Benchmark Almanac

CookBench v1 (CookWing)

GPT-5.6 Sol 40% leads since August 2026
Not in model cards

Models give ingredient quantities for carbonara, pastitsio, and melon pan. A run passes when all required amounts and ratios fall within the dish’s specified ranges.

CookWing publishes five trials per recipe for nine models. Its separate product column reports correct quantities, while the model columns report correct runs.

Made by
Tatsuo, CookWing
Released
August 2026
Kind
Language reasoning
Level
Everyday
Scored
Checked automatically
Answers
Open-ended
Measures
Capability
Language
English
In and out
Text → Text
Interaction
Single turn
Items from
Written by experts
Refresh
One fixed set
Run by
Anyone
Strongest model tested
Claude Fable 5 #12 on the capability index
Last model added
July 2026
Scores refreshed
November 20th, 2026
9
Models scored on its own leaderboard

GPT-5.6 Sol leads with 40% among models released by July 2026

Best score per model from the benchmark's own leaderboard, read on November 20th, 2026. Where a model ran with several settings or harnesses, we keep its best.

The newest model with a score here came out in July 2026, and nobody has tested a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:

  1. 1 GPT-5.6 Sol 40%
  2. 2 GLM-5.1 33.3%
  3. 3 DeepSeek-V4-Pro 33.3%
  4. 4 Claude Opus 4.8 33.3%
  5. 5 Claude Fable 5 33.3%
  6. 6 Claude Sonnet 5 33.3%
  7. 7 Kimi K3 33.3%
  8. 8 Gemini 3.1 Pro 26.7%
  9. 9 Claude Opus 4.6 6.67%

Source: Official CookBench v1 (CookWing) leaderboard

#ModelScoreSettingDateSource
1 GPT-5.6 Sol 40% Jul 2026 Official leaderboard
2 GLM-5.1 33.3% Apr 2026 Official leaderboard
3 DeepSeek-V4-Pro 33.3% Apr 2026 Official leaderboard
4 Claude Opus 4.8 33.3% May 2026 Official leaderboard
5 Claude Fable 5 33.3% Jun 2026 Official leaderboard
6 Claude Sonnet 5 33.3% Jun 2026 Official leaderboard
7 Kimi K3 33.3% Jul 2026 Official leaderboard
8 Gemini 3.1 Pro 26.7% Feb 2026 Official leaderboard
9 Claude Opus 4.6 6.67% Feb 2026 Official leaderboard

Rankings by part

We read 3 parts from the benchmark’s own leaderboard: Carbonara, Pastitsio and Melon Pan. Each ranks models on one part of the test. GLM-5.1 leads 1 of them, and 2 other models lead the rest. Arrows show how far a model moved from its overall rank among the models we track.

Carbonara

9 models we track have a score here.

  1. 1 GLM-5.1 ↑1 100%
  2. 2 DeepSeek-V4-Pro ↑1 100%
  3. 3 Claude Opus 4.8 ↑1 100%
  4. 4 Claude Fable 5 ↑1 100%
  5. 5 Claude Sonnet 5 ↑1 100%
  6. 6 GPT-5.6 Sol ↓5 100%
  7. 7 Kimi K3 100%
  8. 8 Gemini 3.1 Pro 80%
  9. 9 Claude Opus 4.6 20%

Number one over time

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

OpenAI
Own leaderboard Not tested since Aug 2026

Source: Official CookBench v1 (CookWing) leaderboard

Scores over time

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

Plot with other benchmarks
On the benchmark’s own leaderboard Best so far
0% 20% 40% 60% 80% 100% 2026 Near the ceiling (85%) GPT-5.6 Sol GLM-5.1 Gemini 3.1 Pro Claude Opus 4.6 0% 20% 40% 60% 80% 100% 2026 Near the ceiling (85%) GPT-5.6 Sol GLM-5.1

Source: Official CookBench v1 (CookWing) leaderboard

No lab model card reports it yet

We read the headline results of 540 launch posts from 57 labs, and none of them list this benchmark.

More in Knowledge

All 332 in Knowledge
  • MMLU-Pro In use Harder 10-option version of MMLU with reasoning-focused questions across 14 subjects. Intern-S2-397B 89.8%
  • MMLU In use 57-subject multiple-choice exam questions from elementary to professional level. Scored by accuracy. Seed1.8 92.3%
  • SuperGPQA In use 26,529 graduate-level multiple-choice questions across 285 disciplines. Accuracy. Qwen 3.6 Max (Preview) 73.9%
  • WideSearch In use 200 bilingual broad info-seeking tasks: agent collects many atomic facts into a table. Scored by success rate and row/item F1. Tencent Hy4 preview 83.9%
  • BBEH micro average In use Models solve harder replacements for each of the 23 BIG-Bench Hard tasks, 4,520 examples in total. The score is the share of all examples answered correctly. Gemma 4 31B IT 74.4%
  • HLE-Diamond In use Models answer 1,000 cleaned expert questions from Humanity's Last Exam, 500 on reasoning and 500 on knowledge, closed book. Graded on exact answers. Claude Fable 5.2 77.9%

Data audit

9 of 10 checks pass, 1 warning. Look first at the Task access check. We don’t know whether the tasks are public. Every benchmark

Catalog record 1 warning 1 pass
  • Warning Task access We don’t know whether the tasks are public.
  • Pass Confidence Checked against a primary source.
Scores 4 pass 1 note
  • Pass Independent runs Scores from the official leaderboard (9 entries).
  • Pass Models scored 9 models we track.
  • Pass Newest score The newest is from July 2026, for Kimi K3.
  • Note Frontier models None of the top 10 has a score. The strongest tested is Claude Fable 5 (#12).
  • Pass Headroom The best is 40%, under 85%, so it still separates models.
Leaderboard import 3 pass
  • Pass Importer We read the board on cook.redwi.ng: 9 rows for models we track at the last read.
  • Pass Last read November 20th, 2026.
  • Pass Read worked The last read worked.
Consistency 1 pass 1 note
  • Note Lab claims No model has both a lab number and an independent run.
  • Pass Known issues No published audit found problems.

How we check