Benchmark Almanac

HiddenMath

DiffusionGemma 26B A4B 80.6% leads since July 2026
Dropped

Models solve 179 competition-level math problems that experts wrote from scratch. Answers are graded automatically.

In-house Google DeepMind set that was never released.

Made by
Google DeepMind
Released
May 2024
Kind
Competition problems with answers
Level
Competition
Scored
Checked automatically
Answers
Short answer
Tasks
Kept private
Strongest model tested
Gemini 2.0 Pro #139 on the capability index
Last in a launch post
June 2025, dropped before it saturated
Last model added
July 2026
11
Models scored in lab cards
7
Launch posts list it, from 1 lab
7
System cards report it, from 1 lab

DiffusionGemma 26B A4B leads with 80.6% among models released by June 2026

Best score per model as labs report them in their own cards. Labs pick their own settings, so these compare less cleanly than independent runs.

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

  1. 80.6 DiffusionGemma 26B A4B
  2. 65.2 Gemini 2.0 Pro
  3. 63.5 Gemini 2.0 Flash
  4. 63.0 Gemini 2.0 Flash
  5. 60.3 Gemma 3 27B
  6. 55.3 Gemini 2.0 Flash-Lite
  7. 54.5 Gemma 3 12B
  8. 43.0 Gemma 3 4B
  9. 37.7 Gemma 3n E4B
  10. 20.1 Gemini 1.5 Pro
  11. 15.8 Gemma 3 1B
  1. 1 DiffusionGemma 26B A4B 80.6%
  2. 2 Gemini 2.0 Pro 65.2%
  3. 3 Gemini 2.0 Flash Feb 2025 63.5%
  4. 4 Gemini 2.0 Flash Dec 2024 63%
  5. 5 Gemma 3 27B 60.3%
  6. 6 Gemini 2.0 Flash-Lite 55.3%
  7. 7 Gemma 3 12B 54.5%
  8. 8 Gemma 3 4B 43%
  9. 9 Gemma 3n E4B 37.7%
  10. 10 Gemini 1.5 Pro May 2024 20.1%
  11. 11 Gemma 3 1B 15.8%

Source: Labs’ model cards

#ModelScoreSettingDateSource
1 DiffusionGemma 26B A4B 80.6% Jul 2026 Lab model card
2 Gemini 2.0 Pro 65.2% Feb 2025 Lab model card
3 Gemini 2.0 Flash Feb 2025 63.5% Feb 2025 Lab model card
4 Gemini 2.0 Flash Dec 2024 63% Dec 2024 Lab model card
5 Gemma 3 27B 60.3% Mar 2025 Lab model card
6 Gemini 2.0 Flash-Lite 55.3% Feb 2025 Lab model card
7 Gemma 3 12B 54.5% Mar 2025 Lab model card
8 Gemma 3 4B 43% Mar 2025 Lab model card
9 Gemma 3n E4B 37.7% Jun 2025 Lab model card
10 Gemini 1.5 Pro May 2024 20.1% May 2024 Lab model card
11 Gemma 3 1B 15.8% Mar 2025 Lab model card

4 models have held number one in labs’ own numbers since its release in May 2024

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

Google DeepMind
Lab claims Not tested since Jul 2026
DiffusionGemma 26B A4B 80.6%

Source: Labs’ model cards

Scores over time

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

Reported by the lab in its model card Best so far
0% 20% 40% 60% 80% 100% 2024 2025 2026 Near the ceiling (85%) DiffusionGemma 26B A4B Gemini 2.0 Pro Gemini 1.5 Pro 0% 20% 40% 60% 80% 100% 2024 2025 2026 Near the ceiling (85%) DiffusionGemma 26B A4B Gemini 2.0 Pro

Source: Labs’ model cards

No launch post has listed it since June 2025

Launch posts from every lab that has listed it, one tick per post. Tall colored ticks include it, and short gray ones leave it out.

Google DeepMind
DateLaunch postScoreAs the post writes it
Jun 26, 2025 Gemma 3n E4B 37.7 HiddenMath 0-shot (IT)
Mar 12, 2025 Gemma 3 27B 60.3 HiddenMath 0-shot (IT)
Feb 5, 2025 Gemini 2.0 Flash-Lite 55.3 HiddenMath
Feb 5, 2025 Gemini 2.0 Flash 63.5 HiddenMath
Feb 5, 2025 Gemini 2.0 Pro 65.2 HiddenMath
Dec 11, 2024 Gemini 2.0 Flash 63 HiddenMath
May 14, 2024 Gemini 1.5 Pro 20.1 HiddenMath, 0-shot

7 system cards report it, from 1 lab

Besides launch posts, we read the system cards, model cards and technical reports labs publish with a release. They report far more, including safety and frontier-risk tests.

DateDocumentScoreAs the document writes itSection
Jul 31, 2026 DiffusionGemma 26B A4B technical report 80.6 HiddenMath (internal), TD, 74.3 no-think (Table 3) Capabilities
Apr 15, 2025 Gemini 2.0 Flash model card 63.5 HiddenMath (Table, p.3, column Gemini 2.0 Flash (GA)) Capabilities
Apr 10, 2025 Gemini 2.0 Flash-Lite model card 55.3 HiddenMath (Table, p.3) Capabilities
Mar 25, 2025 Gemma 3 4B technical report 43 HiddenMath, IT, zero-shot (Table 6). Table 18 gives 42.0 Capabilities
Mar 25, 2025 Gemma 3 27B technical report 60.3 HiddenMath, IT, zero-shot (Table 6). Table 18 gives 56.0 Capabilities
Mar 25, 2025 Gemma 3 1B technical report 15.8 HiddenMath, IT, zero-shot (Table 6). Table 18 gives 15.0 Capabilities
Mar 25, 2025 Gemma 3 12B technical report 54.5 HiddenMath, IT, zero-shot (Table 6). Table 18 gives 51.0 Capabilities

Versions

Replaced by LiveMath

More in Math

All 113 in Math
  • AIME 2026 In use Models solve the 30 integer-answer problems from the 2026 AIME I and II math competitions. Scored by exact answer match. GPT-5.5 100%
  • IMO-AnswerBench In use 400 olympiad problems with short verifiable answers, robustified against memorization. Scored by answer match. GLM-5.2 91%
  • HMMT 2026 In use Models solve the 33 final-answer problems from the February 2026 Harvard-MIT Mathematics Tournament. Scored by exact answer match. GPT-5.5 98.5%
  • PolyMath In use Models solve 9,000 parallel math problems in 18 languages across four difficulty levels, from school math to frontier math. Final answers are checked. Qwen3.7-Max 86.5%
  • MathArena (Apex, IMO, USAMO) In use Evaluates models on newly released math competitions after release. Final-answer or human/LLM-judged proof scores. Claude Opus 4.8 81.3%
  • MathArena Apex Shortlist In use Models solve 47 hard final-answer problems that MathArena selected from 2025 competitions, where the best models scored about 50% at selection. Scored by accuracy over repeated attempts. GPT-5.5 98.4%