Benchmark Almanac

Chart Arena

GPT-6.1 Sol 1,628 leads since September 2026
Not in model cards

Models create charts. Pairwise votes determine the published Arena rating.

The official API publishes an Arena rating, confidence interval and vote count. Voter identity requires confirmation from the board description.

Made by
Kaggle
Kind
Data science and SQL
Level
Everyday
Scored
Ranked by votes
Answers
Open-ended
Tasks
All public
Strongest model tested
Gemini 4 Carbon #2 on the capability index
Last model added
October 2026
Scores refreshed
November 12th, 2026
15
Models scored on its own leaderboard

GPT-6.1 Sol leads with 1,628

Best score per model from the benchmark's own leaderboard, read on November 12th, 2026. Where a model ran with several settings or harnesses, we keep its best.

15 models. Scroll sideways for the rest. Bars start at 1,300.

  1. 1,628 GPT-6.1 Sol
  2. 1,618 Claude Opus 5.5
  3. 1,605 GPT-6 Astra
  4. 1,598 Claude Fable 5.1
  5. 1,547 Gemini 3.5 Flash-Lite
  6. 1,520 Gemini 4 Argon
  7. 1,509 Grok 4.7
  8. 1,506 Gemini 4 Carbon
  9. 1,472 Gemini 3.8 Flash
  10. 1,469 GLM-5.3-Flash
  11. 1,466 Grok 4.5
  12. 1,457 Claude Sonnet 5.5
  13. 1,415 GPT-6 Luna
  14. 1,366 GPT-5.6 Luna
  15. 1,322 Gemma 4 26B A4B

Bars start at 1,300.

  1. 1 GPT-6.1 Sol 1,628
  2. 2 Claude Opus 5.5 1,618
  3. 3 GPT-6 Astra 1,605
  4. 4 Claude Fable 5.1 1,598
  5. 5 Gemini 3.5 Flash-Lite 1,547
  6. 6 Gemini 4 Argon 1,520
  7. 7 Grok 4.7 1,509
  8. 8 Gemini 4 Carbon 1,506
  9. 9 Gemini 3.8 Flash 1,472
  10. 10 GLM-5.3-Flash 1,469
  11. 11 Grok 4.5 1,466
  12. 12 Claude Sonnet 5.5 1,457
  13. 13 GPT-6 Luna 1,415
  14. 14 GPT-5.6 Luna 1,366
  15. 15 Gemma 4 26B A4B 1,322

Source: Official Chart Arena leaderboard

#ModelScoreSettingDateSource
1 GPT-6.1 Sol 1,628 Sep 2026 Official leaderboard
2 Claude Opus 5.5 1,618 Sep 2026 Official leaderboard
3 GPT-6 Astra 1,605 Sep 2026 Official leaderboard
4 Claude Fable 5.1 1,598 Sep 2026 Official leaderboard
5 Gemini 3.5 Flash-Lite 1,547 Jul 2026 Official leaderboard
6 Gemini 4 Argon 1,520 Sep 2026 Official leaderboard
7 Grok 4.7 1,509 Sep 2026 Official leaderboard
8 Gemini 4 Carbon 1,506 Oct 2026 Official leaderboard
9 Gemini 3.8 Flash 1,472 Sep 2026 Official leaderboard
10 GLM-5.3-Flash 1,469 Aug 2026 Official leaderboard
11 Grok 4.5 1,466 Jul 2026 Official leaderboard
12 Claude Sonnet 5.5 1,457 Sep 2026 Official leaderboard
13 GPT-6 Luna 1,415 Sep 2026 Official leaderboard
14 GPT-5.6 Luna 1,366 Jul 2026 Official leaderboard
15 Gemma 4 26B A4B 1,322 Apr 2026 Official leaderboard

7 models have held number one on the official leaderboard since 2023

Lab claims count from the day the card came out, independent runs from the model’s release.

Google DeepMind xAI Anthropic OpenAI
Own leaderboard 7 leaders
GPT-6.1 Sol 1,628

Source: Official Chart Arena leaderboard

Scores over time

All the scores we have, one dot each, so a model tested at several settings appears more than once.

On the benchmark’s own leaderboard
1,300 1,400 1,500 1,600 1,700 2026 2027 1,300 1,400 1,500 1,600 1,700 2026 2027

Source: Official Chart Arena leaderboard

No lab model card reports it yet

We read the headline results of 522 launch posts from 52 labs, and none of them list this benchmark.

More in Coding

All 282 in Coding
  • SWE-bench Verified In use 500 human-validated GitHub issues from 12 Python repos. Agent writes a patch that must pass hidden tests. Claude Opus 4.7 83.5%
  • LiveCodeBench v6 In use Competitive programming problems collected after model cutoffs from LeetCode, AtCoder, Codeforces. Scored pass@1 on hidden tests. DeepSeek-V4-Pro 93.5%
  • SWE-bench Multilingual In use 300 GitHub-issue tasks across nine programming languages in SWE-bench format. Patch graded by repository tests. Claude Fable 5.2 96.6%
  • DeepSWE In use 113 original long-horizon engineering tasks across 91 repos and five languages, written from scratch. Hand-written verifiers accept alternative solutions. GPT-6 Astra 74.1%
  • SciCode In use Scientist-curated research coding problems split into subproblems across natural sciences. Code checked against test cases. Seed2.1 Pro 59.8%
  • Codeforces rating In use Model solves recent Codeforces contest problems. An Elo-style rating is computed from simulated contest performance. DeepSeek V4.1 Flash 3,471