{"name":"Coarena computer-use benchmark","schemaVersion":"1.0","url":"https://coarena.ai/benchmark","methodology":"https://coarena.ai/benchmark/methodology","updatedAt":"2026-09-07T03:07:51.808Z","recoveryUpdatedAt":"2026-09-07T03:07:39.523Z","matchupsUpdatedAt":"2026-09-07T03:07:51.491Z","degraded":false,"priceTableDate":"2026-09-06","definitions":{"winRate":"Decisive wins / eligible comparisons; ties stay in denominator. Descriptive, unweighted; not a predicted probability.","completionRate":"Agent-reported completion, not independently verified task success.","recoveryRate":"Failed actions whose next action did not fail / failed actions with a successor.","estimatedCostPerCompletionUsd":"List-price token estimate over all measured runs / reported completions. Excludes infrastructure and discounts.","windows":"Ranking and wins: eligible comparisons from latest 20,000 judged arena battles. Recovery: latest 1,000 arena battles. Other metrics: full-history non-synthetic arena runs. Operator experiments excluded.","missing":"null means unavailable or unmeasured, never zero."},"models":[{"name":"Claude Fable 5","slug":"claude-fable-5","providerModel":"claude-fable-5","url":"https://coarena.ai/models/claude-fable-5","rank":1,"rating":1065.2589694159774,"ratingIntervalHalfWidth":28,"ratingBasis":"bradley_terry","ratingStatus":"stable","winRate":0.4336134453781513,"completionRate":0.6949760765550239,"medianDurationMs":109980,"recoveryRate":1,"estimatedCostPerCompletionUsd":2.9618904819277105},{"name":"Claude Fable 5.1","slug":"claude-fable-5-1","providerModel":"claude-fable-5-1","url":"https://coarena.ai/models/claude-fable-5-1","rank":8,"rating":1007.2690028190386,"ratingIntervalHalfWidth":50,"ratingBasis":"bradley_terry","ratingStatus":"ranked","winRate":0.36507936507936506,"completionRate":0.6930379746835443,"medianDurationMs":133475,"recoveryRate":1,"estimatedCostPerCompletionUsd":2.472013470319635},{"name":"Claude Haiku 4.5","slug":"claude-haiku-4-5","providerModel":"claude-haiku-4-5-20251001","url":"https://coarena.ai/models/claude-haiku-4-5","rank":13,"rating":981.9002802178776,"ratingIntervalHalfWidth":28,"ratingBasis":"bradley_terry","ratingStatus":"ranked","winRate":0.36142322097378277,"completionRate":0.6416337285902504,"medianDurationMs":196478,"recoveryRate":0.7674418604651163,"estimatedCostPerCompletionUsd":1.0098178090349077},{"name":"Claude Opus 5","slug":"claude-opus-5","providerModel":"claude-opus-5","url":"https://coarena.ai/models/claude-opus-5","rank":5,"rating":1031.2945639028515,"ratingIntervalHalfWidth":25,"ratingBasis":"bradley_terry","ratingStatus":"stable","winRate":0.39480097481722176,"completionRate":0.7042410714285714,"medianDurationMs":128012.5,"recoveryRate":1,"estimatedCostPerCompletionUsd":1.7291692511885897},{"name":"Claude Sonnet 5","slug":"claude-sonnet-5","providerModel":"claude-sonnet-5","url":"https://coarena.ai/models/claude-sonnet-5","rank":11,"rating":999.2565660666443,"ratingIntervalHalfWidth":28,"ratingBasis":"bradley_terry","ratingStatus":"ranked","winRate":0.36885245901639346,"completionRate":0.783410138248848,"medianDurationMs":58337,"recoveryRate":0.7333333333333333,"estimatedCostPerCompletionUsd":1.0478480717647058},{"name":"Gemini 3.5 Flash","slug":"gemini-3-5-flash","providerModel":"gemini-3.5-flash","url":"https://coarena.ai/models/gemini-3-5-flash","rank":12,"rating":985.4763618527803,"ratingIntervalHalfWidth":34,"ratingBasis":"bradley_terry","ratingStatus":"ranked","winRate":0.3551020408163265,"completionRate":0.6460296096904441,"medianDurationMs":245581,"recoveryRate":0.8888888888888888,"estimatedCostPerCompletionUsd":0.9172252921874999},{"name":"Gemini 3.7 Flash","slug":"gemini-3-7-flash","providerModel":"gemini-3.7-flash","url":"https://coarena.ai/models/gemini-3-7-flash","rank":2,"rating":1061.7584013612077,"ratingIntervalHalfWidth":26,"ratingBasis":"bradley_terry","ratingStatus":"ranked","winRate":0.4516829533116178,"completionRate":0.7731421121251629,"medianDurationMs":112620,"recoveryRate":0.9464285714285714,"estimatedCostPerCompletionUsd":0.28625026138279935},{"name":"Gemini 3.8 Flash","slug":"gemini-3-8-flash","providerModel":"gemini-3.8-flash","url":"https://coarena.ai/models/gemini-3-8-flash","rank":4,"rating":1039.6991711922717,"ratingIntervalHalfWidth":69,"ratingBasis":"bradley_terry","ratingStatus":"ranked","winRate":0.45454545454545453,"completionRate":0.7213822894168467,"medianDurationMs":284406,"recoveryRate":0.9681528662420382,"estimatedCostPerCompletionUsd":0.6348970239520958},{"name":"GLM 5.3 Flash","slug":"glm-5-3-flash","providerModel":"z-ai/glm-5.3-flash","url":"https://coarena.ai/models/glm-5-3-flash","rank":16,"rating":937.5159223968732,"ratingIntervalHalfWidth":66,"ratingBasis":"bradley_terry","ratingStatus":"ranked","winRate":0.3046875,"completionRate":0.3022222222222222,"medianDurationMs":259336.5,"recoveryRate":0.9473684210526315,"estimatedCostPerCompletionUsd":0.16264782683823528},{"name":"GPT-5.6 Luna","slug":"gpt-5-6-luna","providerModel":"gpt-5.6-luna","url":"https://coarena.ai/models/gpt-5-6-luna","rank":6,"rating":1027.877005888716,"ratingIntervalHalfWidth":30,"ratingBasis":"bradley_terry","ratingStatus":"ranked","winRate":0.41654571843251087,"completionRate":0.8937300743889479,"medianDurationMs":66945,"recoveryRate":1,"estimatedCostPerCompletionUsd":0.03964978335315101},{"name":"GPT-5.6 Sol","slug":"gpt-5-6-sol","providerModel":"gpt-5.6-sol","url":"https://coarena.ai/models/gpt-5-6-sol","rank":3,"rating":1041.2837806887133,"ratingIntervalHalfWidth":22,"ratingBasis":"bradley_terry","ratingStatus":"stable","winRate":0.39385474860335196,"completionRate":0.8264855687606112,"medianDurationMs":105460.5,"recoveryRate":0.8253968253968254,"estimatedCostPerCompletionUsd":0.8379104889071487},{"name":"GPT-5.6 Terra","slug":"gpt-5-6-terra","providerModel":"gpt-5.6-terra","url":"https://coarena.ai/models/gpt-5-6-terra","rank":9,"rating":1005.08722408469,"ratingIntervalHalfWidth":33,"ratingBasis":"bradley_terry","ratingStatus":"ranked","winRate":0.34894613583138173,"completionRate":0.8567860116569526,"medianDurationMs":60093,"recoveryRate":1,"estimatedCostPerCompletionUsd":0.42680519144800777},{"name":"GPT-6 Astra","slug":"gpt-6-astra","providerModel":"gpt-6-astra","url":"https://coarena.ai/models/gpt-6-astra","rank":18,"rating":927.6457557599018,"ratingIntervalHalfWidth":97,"ratingBasis":"bradley_terry","ratingStatus":"ranked","winRate":0.3146067415730337,"completionRate":0.6311475409836066,"medianDurationMs":138803.5,"recoveryRate":0.9354838709677419,"estimatedCostPerCompletionUsd":5.2698615584415585},{"name":"Grok 4.6","slug":"grok-4-6","providerModel":"grok-4.6","url":"https://coarena.ai/models/grok-4-6","rank":15,"rating":964.2266376231032,"ratingIntervalHalfWidth":33,"ratingBasis":"bradley_terry","ratingStatus":"ranked","winRate":0.3076923076923077,"completionRate":0.5432835820895522,"medianDurationMs":255630,"recoveryRate":0.8260869565217391,"estimatedCostPerCompletionUsd":1.1702739835164835},{"name":"Inkling","slug":"inkling","providerModel":"inkling","url":"https://coarena.ai/models/inkling","rank":14,"rating":979.2387225402417,"ratingIntervalHalfWidth":32,"ratingBasis":"bradley_terry","ratingStatus":"ranked","winRate":0.35858585858585856,"completionRate":0.7473200612557427,"medianDurationMs":75334,"recoveryRate":0.8888888888888888,"estimatedCostPerCompletionUsd":0.43444606290983606},{"name":"Kimi K3","slug":"kimi-k3","providerModel":"kimi-k3","url":"https://coarena.ai/models/kimi-k3","rank":7,"rating":1019.0010447138349,"ratingIntervalHalfWidth":34,"ratingBasis":"bradley_terry","ratingStatus":"ranked","winRate":0.3948497854077253,"completionRate":0.7110552763819096,"medianDurationMs":137187,"recoveryRate":1,"estimatedCostPerCompletionUsd":1.4008540706713781},{"name":"Muse Spark 1.2","slug":"muse-spark-1-2","providerModel":"muse-spark-1.2-contributor","url":"https://coarena.ai/models/muse-spark-1-2","rank":19,"rating":925.14289350042,"ratingIntervalHalfWidth":44,"ratingBasis":"bradley_terry","ratingStatus":"ranked","winRate":0.27335640138408307,"completionRate":0.4,"medianDurationMs":259533.5,"recoveryRate":0.8243243243243243,"estimatedCostPerCompletionUsd":0.109784212992126},{"name":"Muse Spark 1.3","slug":"muse-spark-1-3","providerModel":"muse-spark-1.3-contributor","url":"https://coarena.ai/models/muse-spark-1-3","rank":17,"rating":932.331870575197,"ratingIntervalHalfWidth":400,"ratingBasis":"online_elo","ratingStatus":"provisional","winRate":0,"completionRate":0.058823529411764705,"medianDurationMs":16742,"recoveryRate":0.8333333333333334,"estimatedCostPerCompletionUsd":0.2602271},{"name":"Qwen3.8 Max","slug":"qwen3-8-max","providerModel":"qwen3p8-max","url":"https://coarena.ai/models/qwen3-8-max","rank":10,"rating":1001.0676959748574,"ratingIntervalHalfWidth":39,"ratingBasis":"bradley_terry","ratingStatus":"ranked","winRate":0.36386138613861385,"completionRate":0.5953109072375128,"medianDurationMs":162430,"recoveryRate":0.9141914191419142,"estimatedCostPerCompletionUsd":1.6732018561643835}],"comparisons":[{"modelA":"claude-fable-5","modelB":"claude-fable-5-1","url":"https://coarena.ai/compare/claude-fable-5-vs-claude-fable-5-1","result":{"winRateA":0.42857142857142855,"winRateB":0.14285714285714285,"tieRate":0.42857142857142855,"provisional":true}},{"modelA":"claude-fable-5","modelB":"claude-haiku-4-5","url":"https://coarena.ai/compare/claude-fable-5-vs-claude-haiku-4-5","result":{"winRateA":0.5111111111111111,"winRateB":0.28888888888888886,"tieRate":0.2,"provisional":false}},{"modelA":"claude-fable-5","modelB":"claude-opus-5","url":"https://coarena.ai/compare/claude-fable-5-vs-claude-opus-5","result":{"winRateA":0.38493723849372385,"winRateB":0.3389121338912134,"tieRate":0.27615062761506276,"provisional":false}},{"modelA":"claude-fable-5","modelB":"claude-sonnet-5","url":"https://coarena.ai/compare/claude-fable-5-vs-claude-sonnet-5","result":{"winRateA":0.54,"winRateB":0.24,"tieRate":0.22,"provisional":false}},{"modelA":"claude-fable-5","modelB":"gemini-3-5-flash","url":"https://coarena.ai/compare/claude-fable-5-vs-gemini-3-5-flash","result":{"winRateA":0.5428571428571428,"winRateB":0.2571428571428571,"tieRate":0.2,"provisional":false}},{"modelA":"claude-fable-5","modelB":"gemini-3-7-flash","url":"https://coarena.ai/compare/claude-fable-5-vs-gemini-3-7-flash","result":{"winRateA":0.3709090909090909,"winRateB":0.44,"tieRate":0.1890909090909091,"provisional":false}},{"modelA":"claude-fable-5","modelB":"gemini-3-8-flash","url":"https://coarena.ai/compare/claude-fable-5-vs-gemini-3-8-flash","result":{"winRateA":0.2,"winRateB":0.8,"tieRate":0,"provisional":true}},{"modelA":"claude-fable-5","modelB":"glm-5-3-flash","url":"https://coarena.ai/compare/claude-fable-5-vs-glm-5-3-flash","result":{"winRateA":0.4166666666666667,"winRateB":0.5,"tieRate":0.08333333333333333,"provisional":true}},{"modelA":"claude-fable-5","modelB":"gpt-5-6-luna","url":"https://coarena.ai/compare/claude-fable-5-vs-gpt-5-6-luna","result":{"winRateA":0.43902439024390244,"winRateB":0.3902439024390244,"tieRate":0.17073170731707318,"provisional":false}},{"modelA":"claude-fable-5","modelB":"gpt-5-6-sol","url":"https://coarena.ai/compare/claude-fable-5-vs-gpt-5-6-sol","result":{"winRateA":0.44642857142857145,"winRateB":0.32142857142857145,"tieRate":0.23214285714285715,"provisional":false}},{"modelA":"claude-fable-5","modelB":"gpt-5-6-terra","url":"https://coarena.ai/compare/claude-fable-5-vs-gpt-5-6-terra","result":{"winRateA":0.5531914893617021,"winRateB":0.23404255319148937,"tieRate":0.2127659574468085,"provisional":false}},{"modelA":"claude-fable-5","modelB":"gpt-6-astra","url":"https://coarena.ai/compare/claude-fable-5-vs-gpt-6-astra","result":{"winRateA":0.5,"winRateB":0.5,"tieRate":0,"provisional":true}},{"modelA":"claude-fable-5","modelB":"grok-4-6","url":"https://coarena.ai/compare/claude-fable-5-vs-grok-4-6","result":{"winRateA":0.625,"winRateB":0.20833333333333334,"tieRate":0.16666666666666666,"provisional":true}},{"modelA":"claude-fable-5","modelB":"inkling","url":"https://coarena.ai/compare/claude-fable-5-vs-inkling","result":{"winRateA":0.4482758620689655,"winRateB":0.3103448275862069,"tieRate":0.2413793103448276,"provisional":true}},{"modelA":"claude-fable-5","modelB":"kimi-k3","url":"https://coarena.ai/compare/claude-fable-5-vs-kimi-k3","result":{"winRateA":0.34615384615384615,"winRateB":0.38461538461538464,"tieRate":0.2692307692307692,"provisional":false}},{"modelA":"claude-fable-5","modelB":"muse-spark-1-2","url":"https://coarena.ai/compare/claude-fable-5-vs-muse-spark-1-2","result":{"winRateA":0.6956521739130435,"winRateB":0.17391304347826086,"tieRate":0.13043478260869565,"provisional":true}},{"modelA":"claude-fable-5","modelB":"muse-spark-1-3","url":"https://coarena.ai/compare/claude-fable-5-vs-muse-spark-1-3","result":{"winRateA":1,"winRateB":0,"tieRate":0,"provisional":true}},{"modelA":"claude-fable-5","modelB":"qwen3-8-max","url":"https://coarena.ai/compare/claude-fable-5-vs-qwen3-8-max","result":{"winRateA":0.47619047619047616,"winRateB":0.38095238095238093,"tieRate":0.14285714285714285,"provisional":true}},{"modelA":"claude-fable-5-1","modelB":"claude-haiku-4-5","url":"https://coarena.ai/compare/claude-fable-5-1-vs-claude-haiku-4-5","result":{"winRateA":0.375,"winRateB":0.375,"tieRate":0.25,"provisional":true}},{"modelA":"claude-fable-5-1","modelB":"claude-opus-5","url":"https://coarena.ai/compare/claude-fable-5-1-vs-claude-opus-5","result":{"winRateA":0.6,"winRateB":0.2,"tieRate":0.2,"provisional":true}},{"modelA":"claude-fable-5-1","modelB":"claude-sonnet-5","url":"https://coarena.ai/compare/claude-fable-5-1-vs-claude-sonnet-5","result":{"winRateA":0.5454545454545454,"winRateB":0.2727272727272727,"tieRate":0.18181818181818182,"provisional":true}},{"modelA":"claude-fable-5-1","modelB":"gemini-3-5-flash","url":"https://coarena.ai/compare/claude-fable-5-1-vs-gemini-3-5-flash","result":{"winRateA":0.2,"winRateB":0.4,"tieRate":0.4,"provisional":true}},{"modelA":"claude-fable-5-1","modelB":"gemini-3-7-flash","url":"https://coarena.ai/compare/claude-fable-5-1-vs-gemini-3-7-flash","result":{"winRateA":0.25,"winRateB":0.5,"tieRate":0.25,"provisional":true}},{"modelA":"claude-fable-5-1","modelB":"gemini-3-8-flash","url":"https://coarena.ai/compare/claude-fable-5-1-vs-gemini-3-8-flash","result":{"winRateA":0.5384615384615384,"winRateB":0.38461538461538464,"tieRate":0.07692307692307693,"provisional":true}},{"modelA":"claude-fable-5-1","modelB":"glm-5-3-flash","url":"https://coarena.ai/compare/claude-fable-5-1-vs-glm-5-3-flash","result":{"winRateA":0.6666666666666666,"winRateB":0.3333333333333333,"tieRate":0,"provisional":true}},{"modelA":"claude-fable-5-1","modelB":"gpt-5-6-luna","url":"https://coarena.ai/compare/claude-fable-5-1-vs-gpt-5-6-luna","result":{"winRateA":0.42857142857142855,"winRateB":0.14285714285714285,"tieRate":0.42857142857142855,"provisional":true}},{"modelA":"claude-fable-5-1","modelB":"gpt-5-6-sol","url":"https://coarena.ai/compare/claude-fable-5-1-vs-gpt-5-6-sol","result":{"winRateA":0.2702702702702703,"winRateB":0.4594594594594595,"tieRate":0.2702702702702703,"provisional":false}},{"modelA":"claude-fable-5-1","modelB":"gpt-5-6-terra","url":"https://coarena.ai/compare/claude-fable-5-1-vs-gpt-5-6-terra","result":{"winRateA":0.5,"winRateB":0.16666666666666666,"tieRate":0.3333333333333333,"provisional":true}},{"modelA":"claude-fable-5-1","modelB":"gpt-6-astra","url":"https://coarena.ai/compare/claude-fable-5-1-vs-gpt-6-astra","result":{"winRateA":0.16666666666666666,"winRateB":0.6666666666666666,"tieRate":0.16666666666666666,"provisional":true}},{"modelA":"claude-fable-5-1","modelB":"grok-4-6","url":"https://coarena.ai/compare/claude-fable-5-1-vs-grok-4-6","result":{"winRateA":0.4,"winRateB":0.3,"tieRate":0.3,"provisional":true}},{"modelA":"claude-fable-5-1","modelB":"inkling","url":"https://coarena.ai/compare/claude-fable-5-1-vs-inkling","result":{"winRateA":0.4444444444444444,"winRateB":0.4444444444444444,"tieRate":0.1111111111111111,"provisional":true}},{"modelA":"claude-fable-5-1","modelB":"kimi-k3","url":"https://coarena.ai/compare/claude-fable-5-1-vs-kimi-k3","result":{"winRateA":0,"winRateB":0.09090909090909091,"tieRate":0.9090909090909091,"provisional":true}},{"modelA":"claude-fable-5-1","modelB":"muse-spark-1-2","url":"https://coarena.ai/compare/claude-fable-5-1-vs-muse-spark-1-2","result":{"winRateA":0.6666666666666666,"winRateB":0.3333333333333333,"tieRate":0,"provisional":true}},{"modelA":"claude-fable-5-1","modelB":"muse-spark-1-3","url":"https://coarena.ai/compare/claude-fable-5-1-vs-muse-spark-1-3","result":null},{"modelA":"claude-fable-5-1","modelB":"qwen3-8-max","url":"https://coarena.ai/compare/claude-fable-5-1-vs-qwen3-8-max","result":{"winRateA":0.2857142857142857,"winRateB":0.42857142857142855,"tieRate":0.2857142857142857,"provisional":true}},{"modelA":"claude-haiku-4-5","modelB":"claude-opus-5","url":"https://coarena.ai/compare/claude-haiku-4-5-vs-claude-opus-5","result":{"winRateA":0.3684210526315789,"winRateB":0.4473684210526316,"tieRate":0.18421052631578946,"provisional":false}},{"modelA":"claude-haiku-4-5","modelB":"claude-sonnet-5","url":"https://coarena.ai/compare/claude-haiku-4-5-vs-claude-sonnet-5","result":{"winRateA":0.2916666666666667,"winRateB":0.5625,"tieRate":0.14583333333333334,"provisional":false}},{"modelA":"claude-haiku-4-5","modelB":"gemini-3-5-flash","url":"https://coarena.ai/compare/claude-haiku-4-5-vs-gemini-3-5-flash","result":{"winRateA":0.4528301886792453,"winRateB":0.3584905660377358,"tieRate":0.18867924528301888,"provisional":false}},{"modelA":"claude-haiku-4-5","modelB":"gemini-3-7-flash","url":"https://coarena.ai/compare/claude-haiku-4-5-vs-gemini-3-7-flash","result":{"winRateA":0.42857142857142855,"winRateB":0.42857142857142855,"tieRate":0.14285714285714285,"provisional":false}},{"modelA":"claude-haiku-4-5","modelB":"gemini-3-8-flash","url":"https://coarena.ai/compare/claude-haiku-4-5-vs-gemini-3-8-flash","result":{"winRateA":0.3333333333333333,"winRateB":0.6666666666666666,"tieRate":0,"provisional":true}},{"modelA":"claude-haiku-4-5","modelB":"glm-5-3-flash","url":"https://coarena.ai/compare/claude-haiku-4-5-vs-glm-5-3-flash","result":{"winRateA":0.25,"winRateB":0.25,"tieRate":0.5,"provisional":true}},{"modelA":"claude-haiku-4-5","modelB":"gpt-5-6-luna","url":"https://coarena.ai/compare/claude-haiku-4-5-vs-gpt-5-6-luna","result":{"winRateA":0.3559322033898305,"winRateB":0.4576271186440678,"tieRate":0.1864406779661017,"provisional":false}},{"modelA":"claude-haiku-4-5","modelB":"gpt-5-6-sol","url":"https://coarena.ai/compare/claude-haiku-4-5-vs-gpt-5-6-sol","result":{"winRateA":0.27906976744186046,"winRateB":0.4418604651162791,"tieRate":0.27906976744186046,"provisional":false}},{"modelA":"claude-haiku-4-5","modelB":"gpt-5-6-terra","url":"https://coarena.ai/compare/claude-haiku-4-5-vs-gpt-5-6-terra","result":{"winRateA":0.2608695652173913,"winRateB":0.5217391304347826,"tieRate":0.21739130434782608,"provisional":false}},{"modelA":"claude-haiku-4-5","modelB":"gpt-6-astra","url":"https://coarena.ai/compare/claude-haiku-4-5-vs-gpt-6-astra","result":{"winRateA":0.25,"winRateB":0.625,"tieRate":0.125,"provisional":true}},{"modelA":"claude-haiku-4-5","modelB":"grok-4-6","url":"https://coarena.ai/compare/claude-haiku-4-5-vs-grok-4-6","result":{"winRateA":0.5135135135135135,"winRateB":0.35135135135135137,"tieRate":0.13513513513513514,"provisional":false}},{"modelA":"claude-haiku-4-5","modelB":"inkling","url":"https://coarena.ai/compare/claude-haiku-4-5-vs-inkling","result":{"winRateA":0.42857142857142855,"winRateB":0.35714285714285715,"tieRate":0.21428571428571427,"provisional":true}},{"modelA":"claude-haiku-4-5","modelB":"kimi-k3","url":"https://coarena.ai/compare/claude-haiku-4-5-vs-kimi-k3","result":{"winRateA":0.45161290322580644,"winRateB":0.3548387096774194,"tieRate":0.1935483870967742,"provisional":false}},{"modelA":"claude-haiku-4-5","modelB":"muse-spark-1-2","url":"https://coarena.ai/compare/claude-haiku-4-5-vs-muse-spark-1-2","result":{"winRateA":0.21052631578947367,"winRateB":0.5263157894736842,"tieRate":0.2631578947368421,"provisional":true}},{"modelA":"claude-haiku-4-5","modelB":"muse-spark-1-3","url":"https://coarena.ai/compare/claude-haiku-4-5-vs-muse-spark-1-3","result":null},{"modelA":"claude-haiku-4-5","modelB":"qwen3-8-max","url":"https://coarena.ai/compare/claude-haiku-4-5-vs-qwen3-8-max","result":{"winRateA":0.4444444444444444,"winRateB":0.3888888888888889,"tieRate":0.16666666666666666,"provisional":true}},{"modelA":"claude-opus-5","modelB":"claude-sonnet-5","url":"https://coarena.ai/compare/claude-opus-5-vs-claude-sonnet-5","result":{"winRateA":0.5370370370370371,"winRateB":0.25925925925925924,"tieRate":0.2037037037037037,"provisional":false}},{"modelA":"claude-opus-5","modelB":"gemini-3-5-flash","url":"https://coarena.ai/compare/claude-opus-5-vs-gemini-3-5-flash","result":{"winRateA":0.45714285714285713,"winRateB":0.3142857142857143,"tieRate":0.22857142857142856,"provisional":false}},{"modelA":"claude-opus-5","modelB":"gemini-3-7-flash","url":"https://coarena.ai/compare/claude-opus-5-vs-gemini-3-7-flash","result":{"winRateA":0.3958333333333333,"winRateB":0.4375,"tieRate":0.16666666666666666,"provisional":false}},{"modelA":"claude-opus-5","modelB":"gemini-3-8-flash","url":"https://coarena.ai/compare/claude-opus-5-vs-gemini-3-8-flash","result":{"winRateA":0,"winRateB":0.6666666666666666,"tieRate":0.3333333333333333,"provisional":true}},{"modelA":"claude-opus-5","modelB":"glm-5-3-flash","url":"https://coarena.ai/compare/claude-opus-5-vs-glm-5-3-flash","result":{"winRateA":0.6,"winRateB":0.2,"tieRate":0.2,"provisional":true}},{"modelA":"claude-opus-5","modelB":"gpt-5-6-luna","url":"https://coarena.ai/compare/claude-opus-5-vs-gpt-5-6-luna","result":{"winRateA":0.4473684210526316,"winRateB":0.2894736842105263,"tieRate":0.2631578947368421,"provisional":false}},{"modelA":"claude-opus-5","modelB":"gpt-5-6-sol","url":"https://coarena.ai/compare/claude-opus-5-vs-gpt-5-6-sol","result":{"winRateA":0.3569620253164557,"winRateB":0.4050632911392405,"tieRate":0.2379746835443038,"provisional":false}},{"modelA":"claude-opus-5","modelB":"gpt-5-6-terra","url":"https://coarena.ai/compare/claude-opus-5-vs-gpt-5-6-terra","result":{"winRateA":0.4406779661016949,"winRateB":0.3728813559322034,"tieRate":0.1864406779661017,"provisional":false}},{"modelA":"claude-opus-5","modelB":"gpt-6-astra","url":"https://coarena.ai/compare/claude-opus-5-vs-gpt-6-astra","result":{"winRateA":0.4,"winRateB":0.2,"tieRate":0.4,"provisional":true}},{"modelA":"claude-opus-5","modelB":"grok-4-6","url":"https://coarena.ai/compare/claude-opus-5-vs-grok-4-6","result":{"winRateA":0.45,"winRateB":0.2,"tieRate":0.35,"provisional":true}},{"modelA":"claude-opus-5","modelB":"inkling","url":"https://coarena.ai/compare/claude-opus-5-vs-inkling","result":{"winRateA":0.3333333333333333,"winRateB":0.4,"tieRate":0.26666666666666666,"provisional":true}},{"modelA":"claude-opus-5","modelB":"kimi-k3","url":"https://coarena.ai/compare/claude-opus-5-vs-kimi-k3","result":{"winRateA":0.47368421052631576,"winRateB":0.42105263157894735,"tieRate":0.10526315789473684,"provisional":true}},{"modelA":"claude-opus-5","modelB":"muse-spark-1-2","url":"https://coarena.ai/compare/claude-opus-5-vs-muse-spark-1-2","result":{"winRateA":0.45,"winRateB":0.45,"tieRate":0.1,"provisional":true}},{"modelA":"claude-opus-5","modelB":"muse-spark-1-3","url":"https://coarena.ai/compare/claude-opus-5-vs-muse-spark-1-3","result":null},{"modelA":"claude-opus-5","modelB":"qwen3-8-max","url":"https://coarena.ai/compare/claude-opus-5-vs-qwen3-8-max","result":{"winRateA":0.3888888888888889,"winRateB":0.3888888888888889,"tieRate":0.2222222222222222,"provisional":true}},{"modelA":"claude-sonnet-5","modelB":"gemini-3-5-flash","url":"https://coarena.ai/compare/claude-sonnet-5-vs-gemini-3-5-flash","result":{"winRateA":0.3076923076923077,"winRateB":0.4423076923076923,"tieRate":0.25,"provisional":false}},{"modelA":"claude-sonnet-5","modelB":"gemini-3-7-flash","url":"https://coarena.ai/compare/claude-sonnet-5-vs-gemini-3-7-flash","result":{"winRateA":0.2786885245901639,"winRateB":0.5245901639344263,"tieRate":0.19672131147540983,"provisional":false}},{"modelA":"claude-sonnet-5","modelB":"gemini-3-8-flash","url":"https://coarena.ai/compare/claude-sonnet-5-vs-gemini-3-8-flash","result":{"winRateA":0.3333333333333333,"winRateB":0.6666666666666666,"tieRate":0,"provisional":true}},{"modelA":"claude-sonnet-5","modelB":"glm-5-3-flash","url":"https://coarena.ai/compare/claude-sonnet-5-vs-glm-5-3-flash","result":{"winRateA":0.6666666666666666,"winRateB":0.2222222222222222,"tieRate":0.1111111111111111,"provisional":true}},{"modelA":"claude-sonnet-5","modelB":"gpt-5-6-luna","url":"https://coarena.ai/compare/claude-sonnet-5-vs-gpt-5-6-luna","result":{"winRateA":0.4166666666666667,"winRateB":0.3958333333333333,"tieRate":0.1875,"provisional":false}},{"modelA":"claude-sonnet-5","modelB":"gpt-5-6-sol","url":"https://coarena.ai/compare/claude-sonnet-5-vs-gpt-5-6-sol","result":{"winRateA":0.3119266055045872,"winRateB":0.44495412844036697,"tieRate":0.24311926605504589,"provisional":false}},{"modelA":"claude-sonnet-5","modelB":"gpt-5-6-terra","url":"https://coarena.ai/compare/claude-sonnet-5-vs-gpt-5-6-terra","result":{"winRateA":0.4230769230769231,"winRateB":0.46153846153846156,"tieRate":0.11538461538461539,"provisional":false}},{"modelA":"claude-sonnet-5","modelB":"gpt-6-astra","url":"https://coarena.ai/compare/claude-sonnet-5-vs-gpt-6-astra","result":{"winRateA":0.5,"winRateB":0.3333333333333333,"tieRate":0.16666666666666666,"provisional":true}},{"modelA":"claude-sonnet-5","modelB":"grok-4-6","url":"https://coarena.ai/compare/claude-sonnet-5-vs-grok-4-6","result":{"winRateA":0.30434782608695654,"winRateB":0.30434782608695654,"tieRate":0.391304347826087,"provisional":true}},{"modelA":"claude-sonnet-5","modelB":"inkling","url":"https://coarena.ai/compare/claude-sonnet-5-vs-inkling","result":{"winRateA":0.6666666666666666,"winRateB":0.23333333333333334,"tieRate":0.1,"provisional":false}},{"modelA":"claude-sonnet-5","modelB":"kimi-k3","url":"https://coarena.ai/compare/claude-sonnet-5-vs-kimi-k3","result":{"winRateA":0.48,"winRateB":0.2,"tieRate":0.32,"provisional":true}},{"modelA":"claude-sonnet-5","modelB":"muse-spark-1-2","url":"https://coarena.ai/compare/claude-sonnet-5-vs-muse-spark-1-2","result":{"winRateA":0.7,"winRateB":0.2,"tieRate":0.1,"provisional":true}},{"modelA":"claude-sonnet-5","modelB":"muse-spark-1-3","url":"https://coarena.ai/compare/claude-sonnet-5-vs-muse-spark-1-3","result":null},{"modelA":"claude-sonnet-5","modelB":"qwen3-8-max","url":"https://coarena.ai/compare/claude-sonnet-5-vs-qwen3-8-max","result":{"winRateA":0.36363636363636365,"winRateB":0.3181818181818182,"tieRate":0.3181818181818182,"provisional":true}},{"modelA":"gemini-3-5-flash","modelB":"gemini-3-7-flash","url":"https://coarena.ai/compare/gemini-3-5-flash-vs-gemini-3-7-flash","result":{"winRateA":0.19444444444444445,"winRateB":0.5,"tieRate":0.3055555555555556,"provisional":false}},{"modelA":"gemini-3-5-flash","modelB":"gemini-3-8-flash","url":"https://coarena.ai/compare/gemini-3-5-flash-vs-gemini-3-8-flash","result":{"winRateA":0.5714285714285714,"winRateB":0.42857142857142855,"tieRate":0,"provisional":true}},{"modelA":"gemini-3-5-flash","modelB":"glm-5-3-flash","url":"https://coarena.ai/compare/gemini-3-5-flash-vs-glm-5-3-flash","result":{"winRateA":0.45454545454545453,"winRateB":0.36363636363636365,"tieRate":0.18181818181818182,"provisional":true}},{"modelA":"gemini-3-5-flash","modelB":"gpt-5-6-luna","url":"https://coarena.ai/compare/gemini-3-5-flash-vs-gpt-5-6-luna","result":{"winRateA":0.2857142857142857,"winRateB":0.47619047619047616,"tieRate":0.23809523809523808,"provisional":false}},{"modelA":"gemini-3-5-flash","modelB":"gpt-5-6-sol","url":"https://coarena.ai/compare/gemini-3-5-flash-vs-gpt-5-6-sol","result":{"winRateA":0.18604651162790697,"winRateB":0.5348837209302325,"tieRate":0.27906976744186046,"provisional":false}},{"modelA":"gemini-3-5-flash","modelB":"gpt-5-6-terra","url":"https://coarena.ai/compare/gemini-3-5-flash-vs-gpt-5-6-terra","result":{"winRateA":0.4444444444444444,"winRateB":0.3333333333333333,"tieRate":0.2222222222222222,"provisional":false}},{"modelA":"gemini-3-5-flash","modelB":"gpt-6-astra","url":"https://coarena.ai/compare/gemini-3-5-flash-vs-gpt-6-astra","result":{"winRateA":0.5,"winRateB":0.25,"tieRate":0.25,"provisional":true}},{"modelA":"gemini-3-5-flash","modelB":"grok-4-6","url":"https://coarena.ai/compare/gemini-3-5-flash-vs-grok-4-6","result":{"winRateA":0.59375,"winRateB":0.125,"tieRate":0.28125,"provisional":false}},{"modelA":"gemini-3-5-flash","modelB":"inkling","url":"https://coarena.ai/compare/gemini-3-5-flash-vs-inkling","result":{"winRateA":0.3548387096774194,"winRateB":0.5483870967741935,"tieRate":0.0967741935483871,"provisional":false}},{"modelA":"gemini-3-5-flash","modelB":"kimi-k3","url":"https://coarena.ai/compare/gemini-3-5-flash-vs-kimi-k3","result":{"winRateA":0.37037037037037035,"winRateB":0.48148148148148145,"tieRate":0.14814814814814814,"provisional":true}},{"modelA":"gemini-3-5-flash","modelB":"muse-spark-1-2","url":"https://coarena.ai/compare/gemini-3-5-flash-vs-muse-spark-1-2","result":{"winRateA":0.3684210526315789,"winRateB":0.2631578947368421,"tieRate":0.3684210526315789,"provisional":true}},{"modelA":"gemini-3-5-flash","modelB":"muse-spark-1-3","url":"https://coarena.ai/compare/gemini-3-5-flash-vs-muse-spark-1-3","result":null},{"modelA":"gemini-3-5-flash","modelB":"qwen3-8-max","url":"https://coarena.ai/compare/gemini-3-5-flash-vs-qwen3-8-max","result":{"winRateA":0.4090909090909091,"winRateB":0.4090909090909091,"tieRate":0.18181818181818182,"provisional":true}},{"modelA":"gemini-3-7-flash","modelB":"gemini-3-8-flash","url":"https://coarena.ai/compare/gemini-3-7-flash-vs-gemini-3-8-flash","result":{"winRateA":0.3181818181818182,"winRateB":0.3181818181818182,"tieRate":0.36363636363636365,"provisional":true}},{"modelA":"gemini-3-7-flash","modelB":"glm-5-3-flash","url":"https://coarena.ai/compare/gemini-3-7-flash-vs-glm-5-3-flash","result":{"winRateA":0.3333333333333333,"winRateB":0.3333333333333333,"tieRate":0.3333333333333333,"provisional":true}},{"modelA":"gemini-3-7-flash","modelB":"gpt-5-6-luna","url":"https://coarena.ai/compare/gemini-3-7-flash-vs-gpt-5-6-luna","result":{"winRateA":0.5370370370370371,"winRateB":0.2962962962962963,"tieRate":0.16666666666666666,"provisional":false}},{"modelA":"gemini-3-7-flash","modelB":"gpt-5-6-sol","url":"https://coarena.ai/compare/gemini-3-7-flash-vs-gpt-5-6-sol","result":{"winRateA":0.4697986577181208,"winRateB":0.3288590604026846,"tieRate":0.20134228187919462,"provisional":false}},{"modelA":"gemini-3-7-flash","modelB":"gpt-5-6-terra","url":"https://coarena.ai/compare/gemini-3-7-flash-vs-gpt-5-6-terra","result":{"winRateA":0.41379310344827586,"winRateB":0.41379310344827586,"tieRate":0.1724137931034483,"provisional":true}},{"modelA":"gemini-3-7-flash","modelB":"gpt-6-astra","url":"https://coarena.ai/compare/gemini-3-7-flash-vs-gpt-6-astra","result":{"winRateA":1,"winRateB":0,"tieRate":0,"provisional":true}},{"modelA":"gemini-3-7-flash","modelB":"grok-4-6","url":"https://coarena.ai/compare/gemini-3-7-flash-vs-grok-4-6","result":{"winRateA":0.46875,"winRateB":0.21875,"tieRate":0.3125,"provisional":false}},{"modelA":"gemini-3-7-flash","modelB":"inkling","url":"https://coarena.ai/compare/gemini-3-7-flash-vs-inkling","result":{"winRateA":0.40625,"winRateB":0.375,"tieRate":0.21875,"provisional":false}},{"modelA":"gemini-3-7-flash","modelB":"kimi-k3","url":"https://coarena.ai/compare/gemini-3-7-flash-vs-kimi-k3","result":{"winRateA":0.3870967741935484,"winRateB":0.3870967741935484,"tieRate":0.22580645161290322,"provisional":false}},{"modelA":"gemini-3-7-flash","modelB":"muse-spark-1-2","url":"https://coarena.ai/compare/gemini-3-7-flash-vs-muse-spark-1-2","result":{"winRateA":0.6875,"winRateB":0,"tieRate":0.3125,"provisional":true}},{"modelA":"gemini-3-7-flash","modelB":"muse-spark-1-3","url":"https://coarena.ai/compare/gemini-3-7-flash-vs-muse-spark-1-3","result":null},{"modelA":"gemini-3-7-flash","modelB":"qwen3-8-max","url":"https://coarena.ai/compare/gemini-3-7-flash-vs-qwen3-8-max","result":{"winRateA":0.35714285714285715,"winRateB":0.3142857142857143,"tieRate":0.32857142857142857,"provisional":false}},{"modelA":"gemini-3-8-flash","modelB":"glm-5-3-flash","url":"https://coarena.ai/compare/gemini-3-8-flash-vs-glm-5-3-flash","result":{"winRateA":1,"winRateB":0,"tieRate":0,"provisional":true}},{"modelA":"gemini-3-8-flash","modelB":"gpt-5-6-luna","url":"https://coarena.ai/compare/gemini-3-8-flash-vs-gpt-5-6-luna","result":{"winRateA":0.75,"winRateB":0,"tieRate":0.25,"provisional":true}},{"modelA":"gemini-3-8-flash","modelB":"gpt-5-6-sol","url":"https://coarena.ai/compare/gemini-3-8-flash-vs-gpt-5-6-sol","result":{"winRateA":0.4146341463414634,"winRateB":0.45121951219512196,"tieRate":0.13414634146341464,"provisional":false}},{"modelA":"gemini-3-8-flash","modelB":"gpt-5-6-terra","url":"https://coarena.ai/compare/gemini-3-8-flash-vs-gpt-5-6-terra","result":{"winRateA":0.75,"winRateB":0.25,"tieRate":0,"provisional":true}},{"modelA":"gemini-3-8-flash","modelB":"gpt-6-astra","url":"https://coarena.ai/compare/gemini-3-8-flash-vs-gpt-6-astra","result":{"winRateA":0.7142857142857143,"winRateB":0,"tieRate":0.2857142857142857,"provisional":true}},{"modelA":"gemini-3-8-flash","modelB":"grok-4-6","url":"https://coarena.ai/compare/gemini-3-8-flash-vs-grok-4-6","result":{"winRateA":0.6363636363636364,"winRateB":0.2727272727272727,"tieRate":0.09090909090909091,"provisional":true}},{"modelA":"gemini-3-8-flash","modelB":"inkling","url":"https://coarena.ai/compare/gemini-3-8-flash-vs-inkling","result":{"winRateA":0.2857142857142857,"winRateB":0.7142857142857143,"tieRate":0,"provisional":true}},{"modelA":"gemini-3-8-flash","modelB":"kimi-k3","url":"https://coarena.ai/compare/gemini-3-8-flash-vs-kimi-k3","result":{"winRateA":0.3333333333333333,"winRateB":0.5,"tieRate":0.16666666666666666,"provisional":true}},{"modelA":"gemini-3-8-flash","modelB":"muse-spark-1-2","url":"https://coarena.ai/compare/gemini-3-8-flash-vs-muse-spark-1-2","result":{"winRateA":0.4444444444444444,"winRateB":0.4444444444444444,"tieRate":0.1111111111111111,"provisional":true}},{"modelA":"gemini-3-8-flash","modelB":"muse-spark-1-3","url":"https://coarena.ai/compare/gemini-3-8-flash-vs-muse-spark-1-3","result":null},{"modelA":"gemini-3-8-flash","modelB":"qwen3-8-max","url":"https://coarena.ai/compare/gemini-3-8-flash-vs-qwen3-8-max","result":{"winRateA":0.2857142857142857,"winRateB":0.2857142857142857,"tieRate":0.42857142857142855,"provisional":true}},{"modelA":"glm-5-3-flash","modelB":"gpt-5-6-luna","url":"https://coarena.ai/compare/glm-5-3-flash-vs-gpt-5-6-luna","result":{"winRateA":0.25,"winRateB":0.375,"tieRate":0.375,"provisional":true}},{"modelA":"glm-5-3-flash","modelB":"gpt-5-6-sol","url":"https://coarena.ai/compare/glm-5-3-flash-vs-gpt-5-6-sol","result":{"winRateA":0.375,"winRateB":0.5,"tieRate":0.125,"provisional":true}},{"modelA":"glm-5-3-flash","modelB":"gpt-5-6-terra","url":"https://coarena.ai/compare/glm-5-3-flash-vs-gpt-5-6-terra","result":{"winRateA":0.14285714285714285,"winRateB":0.7142857142857143,"tieRate":0.14285714285714285,"provisional":true}},{"modelA":"glm-5-3-flash","modelB":"gpt-6-astra","url":"https://coarena.ai/compare/glm-5-3-flash-vs-gpt-6-astra","result":{"winRateA":0,"winRateB":0.5,"tieRate":0.5,"provisional":true}},{"modelA":"glm-5-3-flash","modelB":"grok-4-6","url":"https://coarena.ai/compare/glm-5-3-flash-vs-grok-4-6","result":{"winRateA":0.36363636363636365,"winRateB":0.5454545454545454,"tieRate":0.09090909090909091,"provisional":true}},{"modelA":"glm-5-3-flash","modelB":"inkling","url":"https://coarena.ai/compare/glm-5-3-flash-vs-inkling","result":{"winRateA":0.375,"winRateB":0.25,"tieRate":0.375,"provisional":true}},{"modelA":"glm-5-3-flash","modelB":"kimi-k3","url":"https://coarena.ai/compare/glm-5-3-flash-vs-kimi-k3","result":{"winRateA":0.375,"winRateB":0.5,"tieRate":0.125,"provisional":true}},{"modelA":"glm-5-3-flash","modelB":"muse-spark-1-2","url":"https://coarena.ai/compare/glm-5-3-flash-vs-muse-spark-1-2","result":{"winRateA":0.3333333333333333,"winRateB":0.2222222222222222,"tieRate":0.4444444444444444,"provisional":true}},{"modelA":"glm-5-3-flash","modelB":"muse-spark-1-3","url":"https://coarena.ai/compare/glm-5-3-flash-vs-muse-spark-1-3","result":{"winRateA":1,"winRateB":0,"tieRate":0,"provisional":true}},{"modelA":"glm-5-3-flash","modelB":"qwen3-8-max","url":"https://coarena.ai/compare/glm-5-3-flash-vs-qwen3-8-max","result":{"winRateA":0,"winRateB":0.6666666666666666,"tieRate":0.3333333333333333,"provisional":true}},{"modelA":"gpt-5-6-luna","modelB":"gpt-5-6-sol","url":"https://coarena.ai/compare/gpt-5-6-luna-vs-gpt-5-6-sol","result":{"winRateA":0.46153846153846156,"winRateB":0.3247863247863248,"tieRate":0.21367521367521367,"provisional":false}},{"modelA":"gpt-5-6-luna","modelB":"gpt-5-6-terra","url":"https://coarena.ai/compare/gpt-5-6-luna-vs-gpt-5-6-terra","result":{"winRateA":0.391304347826087,"winRateB":0.391304347826087,"tieRate":0.21739130434782608,"provisional":false}},{"modelA":"gpt-5-6-luna","modelB":"gpt-6-astra","url":"https://coarena.ai/compare/gpt-5-6-luna-vs-gpt-6-astra","result":{"winRateA":0.5555555555555556,"winRateB":0.4444444444444444,"tieRate":0,"provisional":true}},{"modelA":"gpt-5-6-luna","modelB":"grok-4-6","url":"https://coarena.ai/compare/gpt-5-6-luna-vs-grok-4-6","result":{"winRateA":0.3548387096774194,"winRateB":0.41935483870967744,"tieRate":0.22580645161290322,"provisional":false}},{"modelA":"gpt-5-6-luna","modelB":"inkling","url":"https://coarena.ai/compare/gpt-5-6-luna-vs-inkling","result":{"winRateA":0.5641025641025641,"winRateB":0.23076923076923078,"tieRate":0.20512820512820512,"provisional":false}},{"modelA":"gpt-5-6-luna","modelB":"kimi-k3","url":"https://coarena.ai/compare/gpt-5-6-luna-vs-kimi-k3","result":{"winRateA":0.4482758620689655,"winRateB":0.4482758620689655,"tieRate":0.10344827586206896,"provisional":true}},{"modelA":"gpt-5-6-luna","modelB":"muse-spark-1-2","url":"https://coarena.ai/compare/gpt-5-6-luna-vs-muse-spark-1-2","result":{"winRateA":0.5555555555555556,"winRateB":0.25925925925925924,"tieRate":0.18518518518518517,"provisional":true}},{"modelA":"gpt-5-6-luna","modelB":"muse-spark-1-3","url":"https://coarena.ai/compare/gpt-5-6-luna-vs-muse-spark-1-3","result":null},{"modelA":"gpt-5-6-luna","modelB":"qwen3-8-max","url":"https://coarena.ai/compare/gpt-5-6-luna-vs-qwen3-8-max","result":{"winRateA":0.5517241379310345,"winRateB":0.27586206896551724,"tieRate":0.1724137931034483,"provisional":true}},{"modelA":"gpt-5-6-sol","modelB":"gpt-5-6-terra","url":"https://coarena.ai/compare/gpt-5-6-sol-vs-gpt-5-6-terra","result":{"winRateA":0.3415841584158416,"winRateB":0.22772277227722773,"tieRate":0.4306930693069307,"provisional":false}},{"modelA":"gpt-5-6-sol","modelB":"gpt-6-astra","url":"https://coarena.ai/compare/gpt-5-6-sol-vs-gpt-6-astra","result":{"winRateA":0.6666666666666666,"winRateB":0.3333333333333333,"tieRate":0,"provisional":true}},{"modelA":"gpt-5-6-sol","modelB":"grok-4-6","url":"https://coarena.ai/compare/gpt-5-6-sol-vs-grok-4-6","result":{"winRateA":0.5185185185185185,"winRateB":0.07407407407407407,"tieRate":0.4074074074074074,"provisional":true}},{"modelA":"gpt-5-6-sol","modelB":"inkling","url":"https://coarena.ai/compare/gpt-5-6-sol-vs-inkling","result":{"winRateA":0.5,"winRateB":0.26666666666666666,"tieRate":0.23333333333333334,"provisional":false}},{"modelA":"gpt-5-6-sol","modelB":"kimi-k3","url":"https://coarena.ai/compare/gpt-5-6-sol-vs-kimi-k3","result":{"winRateA":0.475,"winRateB":0.2875,"tieRate":0.2375,"provisional":false}},{"modelA":"gpt-5-6-sol","modelB":"muse-spark-1-2","url":"https://coarena.ai/compare/gpt-5-6-sol-vs-muse-spark-1-2","result":{"winRateA":0.5,"winRateB":0.2,"tieRate":0.3,"provisional":true}},{"modelA":"gpt-5-6-sol","modelB":"muse-spark-1-3","url":"https://coarena.ai/compare/gpt-5-6-sol-vs-muse-spark-1-3","result":null},{"modelA":"gpt-5-6-sol","modelB":"qwen3-8-max","url":"https://coarena.ai/compare/gpt-5-6-sol-vs-qwen3-8-max","result":{"winRateA":0.4107142857142857,"winRateB":0.4107142857142857,"tieRate":0.17857142857142858,"provisional":false}},{"modelA":"gpt-5-6-terra","modelB":"gpt-6-astra","url":"https://coarena.ai/compare/gpt-5-6-terra-vs-gpt-6-astra","result":{"winRateA":1,"winRateB":0,"tieRate":0,"provisional":true}},{"modelA":"gpt-5-6-terra","modelB":"grok-4-6","url":"https://coarena.ai/compare/gpt-5-6-terra-vs-grok-4-6","result":{"winRateA":0.25,"winRateB":0.4583333333333333,"tieRate":0.2916666666666667,"provisional":true}},{"modelA":"gpt-5-6-terra","modelB":"inkling","url":"https://coarena.ai/compare/gpt-5-6-terra-vs-inkling","result":{"winRateA":0.3333333333333333,"winRateB":0.3333333333333333,"tieRate":0.3333333333333333,"provisional":true}},{"modelA":"gpt-5-6-terra","modelB":"kimi-k3","url":"https://coarena.ai/compare/gpt-5-6-terra-vs-kimi-k3","result":{"winRateA":0.3333333333333333,"winRateB":0.4074074074074074,"tieRate":0.25925925925925924,"provisional":true}},{"modelA":"gpt-5-6-terra","modelB":"muse-spark-1-2","url":"https://coarena.ai/compare/gpt-5-6-terra-vs-muse-spark-1-2","result":{"winRateA":0.5625,"winRateB":0.25,"tieRate":0.1875,"provisional":true}},{"modelA":"gpt-5-6-terra","modelB":"muse-spark-1-3","url":"https://coarena.ai/compare/gpt-5-6-terra-vs-muse-spark-1-3","result":{"winRateA":1,"winRateB":0,"tieRate":0,"provisional":true}},{"modelA":"gpt-5-6-terra","modelB":"qwen3-8-max","url":"https://coarena.ai/compare/gpt-5-6-terra-vs-qwen3-8-max","result":{"winRateA":0.5882352941176471,"winRateB":0.29411764705882354,"tieRate":0.11764705882352941,"provisional":true}},{"modelA":"gpt-6-astra","modelB":"grok-4-6","url":"https://coarena.ai/compare/gpt-6-astra-vs-grok-4-6","result":{"winRateA":0.3333333333333333,"winRateB":0.3333333333333333,"tieRate":0.3333333333333333,"provisional":true}},{"modelA":"gpt-6-astra","modelB":"inkling","url":"https://coarena.ai/compare/gpt-6-astra-vs-inkling","result":{"winRateA":0.6666666666666666,"winRateB":0.3333333333333333,"tieRate":0,"provisional":true}},{"modelA":"gpt-6-astra","modelB":"kimi-k3","url":"https://coarena.ai/compare/gpt-6-astra-vs-kimi-k3","result":{"winRateA":0.2,"winRateB":0.6,"tieRate":0.2,"provisional":true}},{"modelA":"gpt-6-astra","modelB":"muse-spark-1-2","url":"https://coarena.ai/compare/gpt-6-astra-vs-muse-spark-1-2","result":{"winRateA":0.18181818181818182,"winRateB":0.7272727272727273,"tieRate":0.09090909090909091,"provisional":true}},{"modelA":"gpt-6-astra","modelB":"muse-spark-1-3","url":"https://coarena.ai/compare/gpt-6-astra-vs-muse-spark-1-3","result":null},{"modelA":"gpt-6-astra","modelB":"qwen3-8-max","url":"https://coarena.ai/compare/gpt-6-astra-vs-qwen3-8-max","result":{"winRateA":0,"winRateB":0.6,"tieRate":0.4,"provisional":true}},{"modelA":"grok-4-6","modelB":"inkling","url":"https://coarena.ai/compare/grok-4-6-vs-inkling","result":{"winRateA":0.4,"winRateB":0.4,"tieRate":0.2,"provisional":false}},{"modelA":"grok-4-6","modelB":"kimi-k3","url":"https://coarena.ai/compare/grok-4-6-vs-kimi-k3","result":{"winRateA":0.42857142857142855,"winRateB":0.5,"tieRate":0.07142857142857142,"provisional":true}},{"modelA":"grok-4-6","modelB":"muse-spark-1-2","url":"https://coarena.ai/compare/grok-4-6-vs-muse-spark-1-2","result":{"winRateA":0.4375,"winRateB":0.25,"tieRate":0.3125,"provisional":true}},{"modelA":"grok-4-6","modelB":"muse-spark-1-3","url":"https://coarena.ai/compare/grok-4-6-vs-muse-spark-1-3","result":null},{"modelA":"grok-4-6","modelB":"qwen3-8-max","url":"https://coarena.ai/compare/grok-4-6-vs-qwen3-8-max","result":{"winRateA":0.32142857142857145,"winRateB":0.32142857142857145,"tieRate":0.35714285714285715,"provisional":true}},{"modelA":"inkling","modelB":"kimi-k3","url":"https://coarena.ai/compare/inkling-vs-kimi-k3","result":{"winRateA":0.35294117647058826,"winRateB":0.47058823529411764,"tieRate":0.17647058823529413,"provisional":false}},{"modelA":"inkling","modelB":"muse-spark-1-2","url":"https://coarena.ai/compare/inkling-vs-muse-spark-1-2","result":{"winRateA":0.5217391304347826,"winRateB":0.21739130434782608,"tieRate":0.2608695652173913,"provisional":true}},{"modelA":"inkling","modelB":"muse-spark-1-3","url":"https://coarena.ai/compare/inkling-vs-muse-spark-1-3","result":null},{"modelA":"inkling","modelB":"qwen3-8-max","url":"https://coarena.ai/compare/inkling-vs-qwen3-8-max","result":{"winRateA":0.3333333333333333,"winRateB":0.42857142857142855,"tieRate":0.23809523809523808,"provisional":true}},{"modelA":"kimi-k3","modelB":"muse-spark-1-2","url":"https://coarena.ai/compare/kimi-k3-vs-muse-spark-1-2","result":{"winRateA":0.7894736842105263,"winRateB":0.15789473684210525,"tieRate":0.05263157894736842,"provisional":true}},{"modelA":"kimi-k3","modelB":"muse-spark-1-3","url":"https://coarena.ai/compare/kimi-k3-vs-muse-spark-1-3","result":null},{"modelA":"kimi-k3","modelB":"qwen3-8-max","url":"https://coarena.ai/compare/kimi-k3-vs-qwen3-8-max","result":{"winRateA":0.35294117647058826,"winRateB":0.4117647058823529,"tieRate":0.23529411764705882,"provisional":false}},{"modelA":"muse-spark-1-2","modelB":"muse-spark-1-3","url":"https://coarena.ai/compare/muse-spark-1-2-vs-muse-spark-1-3","result":null},{"modelA":"muse-spark-1-2","modelB":"qwen3-8-max","url":"https://coarena.ai/compare/muse-spark-1-2-vs-qwen3-8-max","result":{"winRateA":0.25,"winRateB":0.25,"tieRate":0.5,"provisional":true}},{"modelA":"muse-spark-1-3","modelB":"qwen3-8-max","url":"https://coarena.ai/compare/muse-spark-1-3-vs-qwen3-8-max","result":null}]}