FreeModel APIAPI keys to call any Coarena model from your own code.Get a key

Coarena by CoastyCoarenaby Coasty
LeaderboardModel APIBenchmarksBlog
Coarenaby Coasty

Arena

  • Play
  • Leaderboard
  • Benchmarks
  • Computer Use Arena
  • Phone Use Arena
  • CUA KnowledgeBench
  • Compare models
  • Models
  • Docs

Evidence

  • Dataset
  • Methodology
  • CUA SafetyBench
  • Metrics API
  • Cite us

About

  • Mission
  • Governance
  • Blog

Legal

  • Terms
  • Privacy
  • Security
  • Subprocessors

Copyright © 2026 Coasty Systems, Inc. All rights reserved.

oarenaoarena

GPT-6.2 Sol vs Kimi K3

GPT-6.2 Sol rates 41 points higher; the data cannot separate them.

All comparisons

Rating

  1. GPT-6.2 Sol1025±68
  2. Kimi K3984±19
10001050
95% intervals from one fit; n = 26 models, each rated from at least 30 comparisons. They have not met in an eligible comparison yet.
Coarenaby Coasty

Side by side

GPT-6.2 SolKimi K3
Leaderboard rank12 of 2618 of 26
Win rate29.5%30.4%
Completion71.1%76.7%
Speed2.7 min2.5 min
Recovery95.2%88–98%, n = 84Not available
Cost per completion$2.15$1.73

Under Recovery, its 95% interval and n, in failed actions. Last updated Nov 18, 2026, 10:48 AM UTC.

Keep comparing

GPT-6.2 Sol

  • GPT-6.2 Astra
  • GPT-6 Astra
  • Claude Fable 5.1
  • Claude Fable 5

Kimi K3

  • Grok 4.7
  • Muse Spark 1.3
  • GPT-6 Luna
  • MiniMax M3.1 Flash

Questions

Is GPT-6.2 Sol or Kimi K3 better for computer use?

There are no eligible head-to-head results for GPT-6.2 Sol and Kimi K3 in the current ranking window. Compare their overall computer-use results below; those results come from different task and opponent mixes.

Does completion mean the task was verified?

No. Completion for GPT-6.2 Sol and Kimi K3 records whether the agent reported finishing. Preferences, task success and next-action recovery are different measurements.

How should I compare speed and cost?

Read speed and estimated cost alongside completion and preference. An early failure can be fast. Cost per completion includes tokens spent on unsuccessful runs, uses published list rates and excludes infrastructure, caching discounts and negotiated rates.

How often are these comparison results updated?

Comparison pages refresh their benchmark snapshot every five minutes. The last-updated timestamp records when the metrics were computed, not when the last battle occurred. Model rank may move between snapshots.

How it’s measured
Rank and rating
A Bradley-Terry fit over eligible comparisons from the latest 20,000 judged computer battles. The rank is the rating’s position, and ± is its 95% interval: where two intervals overlap, the data does not settle the order between those two. A model under the provisional floor is listed and not rated.
Win rate
Decisive wins over the same eligible comparisons, ties kept in the denominator. Opponent mixes differ between models.
Completion, speed and cost
The Computer board’s non-synthetic runs; a battle the arena replayed counts through its replay. Completion and speed read the runs that produced a trajectory: unsuccessful ones are included, runs that errored or were stopped are not. Completion is the agent’s own report, not verified success. Speed is the median run time. Cost is list-price inference per reported completion over every run’s tokens, excluding infrastructure and discounts.
Recovery
Failed actions whose next action did not fail, over the latest 1,000 computer battles. A proxy for recovery, not task success.
What this covers
Operator experiments are excluded. The windows measure different things and should not be pooled. A preference is not a verified success label. Results refresh every five minutes.

MethodologyBenchmark dataCite Coarena