Benchmark Almanac

ICML 2025 Experts Benchmark

Gemini 2.5 Pro Jun 2025 81.1% leads since July 2025
Not in model cards

Models answer tasks submitted by participants at ICML 2025 in Vancouver. Kaggle reports overall performance and individual task outcomes.

Made by
Kaggle
Released
July 2025
Kind
Language reasoning
Level
University
Scored
Settled by events
Answers
Open-ended
Tasks
All public
Measures
Capability
Language
English
In and out
Text → Text
Interaction
Single turn
Refresh
One fixed set
Run by
Anyone
Strongest model tested
o4-mini #95 on the capability index
Last model added
June 2025
Scores refreshed
November 20th, 2026
6
Models scored on its own leaderboard

Gemini 2.5 Pro leads with 81.1% among models released by June 2025

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 June 2025, and nobody has tested a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:

  1. 1 Gemini 2.5 Pro Jun 2025 81.1%
  2. 2 o4-mini 75.7%
  3. 3 Claude Sonnet 4 70.3%
  4. 4 Gemini 2.0 Flash Feb 2025 64.9%
  5. 5 Claude 3.5 Sonnet 56.8%
  6. 6 DeepSeek-R1 May 2025 51.4%

Source: Official ICML 2025 Experts Benchmark leaderboard

#ModelScoreSettingReleasedRun onSource
1 Gemini 2.5 Pro Jun 2025 81.1% Jun 2025 Jul 2025 Official leaderboard
2 o4-mini 75.7% Apr 2025 Jul 2025 Official leaderboard
3 Claude Sonnet 4 70.3% May 2025 Jul 2025 Official leaderboard
4 Gemini 2.0 Flash Feb 2025 64.9% Feb 2025 Jul 2025 Official leaderboard
5 Claude 3.5 Sonnet 56.8% Jun 2024 Jul 2025 Official leaderboard
6 DeepSeek-R1 May 2025 51.4% May 2025 Jul 2025 Official leaderboard

Rankings by part

We read 37 parts from the benchmark’s own leaderboard, each ranking models on one part of the test, such as Generate ML conference networking questions, Zeno's Paradox: Flashing Light and Reversed Fibonacci sequence. Claude 3.5 Sonnet leads 24 of them, and 4 other models lead the rest. Arrows show how far a model moved from its overall rank among the models we track.

Generate ML conference networking questions

6 models we track have a score here.

  1. 1 Claude 3.5 Sonnet ↑4 100%
  2. 2 Gemini 2.0 Flash Feb 2025 ↑2 100%
  3. 3 o4-mini ↓1 100%
  4. 4 Claude Sonnet 4 ↓1 100%
  5. 5 DeepSeek-R1 May 2025 ↑1 100%
  6. 6 Gemini 2.5 Pro Jun 2025 ↓5 100%

Number one over time

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

Google DeepMind
Own leaderboard Not tested since Jul 2025

Source: Official ICML 2025 Experts Benchmark 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% 2024 2025 Near the ceiling (85%) Gemini 2.5 Pro o4-mini Gemini 2.0 Flash Claude 3.5 Sonnet 0% 20% 40% 60% 80% 100% 2024 2025 Near the ceiling (85%) Gemini 2.5 Pro Gemini 2.0 Flash

Source: Official ICML 2025 Experts Benchmark 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 17 months ago, in June 2025, for Gemini 2.5 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 official leaderboard (6 entries).
  • Pass Models scored 6 models we track.
  • Warning Newest score The newest came 17 months ago, in June 2025, for Gemini 2.5 Pro.
  • Note Frontier models None of the top 10 has a score. The strongest tested is o4-mini (#95).
  • Pass Headroom The best is 81.1%, under 85%, so it still separates models.
Leaderboard import 3 pass
  • Pass Importer We read the board on kaggle.com: 6 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