Benchmark Almanac

GroundCocoa

GPT-4 Turbo (snapshot unspecified) 66.9% tops its leaderboard Gemini 1.0 Pro 41.9% leads the models we track
Not in model cards

Models combine stated conditions with everyday knowledge to choose an answer. The questions test whether the model applies several constraints together.

Made by
Harsh Kohli and colleagues
Released
April 2024
Kind
Language reasoning
Level
Everyday
Scored
Checked automatically
Answers
Multiple choice
Tasks
All public
Measures
Capability
Language
English
In and out
Text → Text
Interaction
Single turn
Refresh
One fixed set
Run by
Anyone
Last model added
December 2023
Scores refreshed
November 20th, 2026
9
Entries in its paper, 2 models we track

GPT-4 Turbo (snapshot unspecified) tops the leaderboard with 66.9% Gemini 1.0 Pro leads with 41.9%

Best score per entry from the benchmark's paper, read on November 20th, 2026. A paper’s table doesn’t add newer models. Where a model ran with several settings or harnesses, we keep its best. Names in gray aren't in our model list: fine-tunes, agent systems, products and older models. They don't count toward leaders. The best model we track is Gemini 1.0 Pro, at 41.9%. This view shows only models we track, each at its best.

  1. 1 GPT-4 Turbo (snapshot unspecified) CoT-partial 66.9%
  2. 2 LLAMA 3.1-chat 70B CoT-partial 59.6%
  3. 3 Mixtral 8x7B-Instruct 44.5%
  4. 4 Gemini 1.0 Pro 41.9%
  5. 5 LLAMA 3.1-chat 8B 34.3%
  6. 6 Mistral-7B-Instruct-v0.1 25.9%
  7. 7 LLAMA 2-chat 70B CoT-partial 25%
  8. 8 LLAMA 2-chat 13B 16.2%
  9. 9 LLAMA 2-chat 7B 14.6%

Source: The GroundCocoa paper

Source: The GroundCocoa paper

#EntryScoreSettingDateSource
1 GPT-4 Turbo (snapshot unspecified) 66.9% CoT-partial Official leaderboard
2 LLAMA 3.1-chat 70B 59.6% CoT-partial Official leaderboard
3 Mixtral 8x7B-Instruct 44.5% Official leaderboard
4 Gemini 1.0 Pro 41.9% Dec 2023 Official leaderboard
5 LLAMA 3.1-chat 8B 34.3% Official leaderboard
6 Mistral-7B-Instruct-v0.1 25.9% Sep 2023 Official leaderboard
7 LLAMA 2-chat 70B 25% CoT-partial Official leaderboard
8 LLAMA 2-chat 13B 16.2% Official leaderboard
9 LLAMA 2-chat 7B 14.6% Official leaderboard
#ModelScoreSettingDateSource
1 Gemini 1.0 Pro 41.9% Dec 2023 Official leaderboard
2 Mistral-7B-Instruct-v0.1 25.9% Sep 2023 Official leaderboard

Number one over time

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

Google DeepMind
Benchmark paper Not tested since Apr 2024

Source: The GroundCocoa paper

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
In the benchmark’s paper Best so far
0% 20% 40% 60% 80% 100% 2024 Near the ceiling (85%) Gemini 1.0 Pro Mistral-7B-Instruct-v0.1 0% 20% 40% 60% 80% 100% 2024 Near the ceiling (85%) Gemini 1.0 Pro Mistral-7B-Instruct-v0.1

Source: Official GroundCocoa 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 Newest score check. The newest came 2 years ago, in December 2023, for Gemini 1.0 Pro. Every benchmark

Catalog record 2 pass
  • Pass Task access All tasks are public.
  • Pass Confidence Checked against a primary source.
Scores 1 warning 3 pass 1 note
  • Pass Independent runs Scores from the benchmark’s paper (9 entries).
  • Pass Models scored 2 models we track, plus 7 other entries on its leaderboard.
  • Warning Newest score The newest came 2 years ago, in December 2023, for Gemini 1.0 Pro.
  • Note Frontier models None of its models are on the capabilities index.
  • Pass Headroom The best is 41.9%, under 85%, so it still separates models.
Leaderboard import 3 pass
  • Pass Importer We read the board on arxiv.org: 4 rows for models we track and 7 other entries 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