Benchmark Almanac

HLE-Diamond

Claude Fable 5.2 77.9% leads since November 2026
Claude Fable 5.2 77.9% leads since November 2026
In use 1 known issue

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.

The makers built it after a year of cleaning as a migration path for when the original set hits its noise ceiling.

Released
September 2026
Kind
Expert-written questions
Level
Research frontier
Scored
Checked automatically
Answers
Short answer
Tasks
All public
Strongest model tested
Claude Fable 5.2 #1 on the capability index
Last in a launch post
November 2026
Last model added
November 2026
Scores refreshed
November 12th, 2026

Known issues

A published audit found a problem in HLE-Diamond. We summarize each finding in our words and link its source. The scores on this page don't include any fixes. See all audits

  1. Leaked answers Reward hacking Still open

    Prime Intellect reports that HLE-Diamond answers leak through mirrors and public rollout logs, so domain blocklists do not stop agents from finding them. In one trace, DeepSeek V4.1-Flash 1017 read a graded answer through OpenReward's public API and submitted it.

    DeepSeek V4.1-Flash 1017 dropped its own answer (0.070) and submitted the leaked answer 0.011 with 98% confidence.

    It went through OpenReward’s public rollout API, found another model’s trajectory on the same question, and read the grader’s verdict: Correct Answer: 0.011.

    Learnings from Auditing Public Evaluations by Prime Intellect, November 3rd, 2026

20
Models scored on its own leaderboard
2
Launch posts list it, from 2 labs

Claude Fable 5.2 leads with 77.9%

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. Every run is in the next chart.

Claude Fable 5.2 leads with 77.9%, claims included

Best score per model from every source, including labs’ own numbers and claims Epoch AI collected from reports and papers. Labs pick their own settings, so a claim can beat an independent run of the same model.

20 models. Scroll sideways for the rest.

  1. 77.9 Claude Fable 5.2
  2. 65.8 GPT-6 Astra
  3. 63.6 Gemini 4 Carbon
  4. 61.3 GPT-6.1 Sol
  5. 60.9 Claude Opus 5.5
  6. 56.9 Gemini 4 Argon
  7. 55.1 Claude Fable 5.1
  8. 43.3 Claude Sonnet 5.5
  9. 43.2 GPT-6 Sol
  10. 41.0 GPT-5.6 Sol
  11. 40.6 Muse Wonder
  12. 40.5 Claude Opus 5
  13. 38.7 Kimi K3.1 Pro
  14. 34.6 Muse Spark 1.3
  15. 33.3 Gemini 3.8 Flash
  16. 28.3 Kimi K3
  17. 28.2 Muse Spark Open
  18. 25.1 GLM-5.3
  19. 25.0 Grok 4.7
  20. 16.6 DeepSeek-V4-Pro
  1. 1 Claude Fable 5.2 max 77.9%
  2. 2 GPT-6 Astra max 65.8%
  3. 3 Gemini 4 Carbon high 63.6%
  4. 4 GPT-6.1 Sol max 61.3%
  5. 5 Claude Opus 5.5 max 60.9%
  6. 6 Gemini 4 Argon high 56.9%
  7. 7 Claude Fable 5.1 max 55.1%
  8. 8 Claude Sonnet 5.5 max 43.3%
  9. 9 GPT-6 Sol max 43.2%
  10. 10 GPT-5.6 Sol max 41%
  11. 11 Muse Wonder max 40.6%
  12. 12 Claude Opus 5 max 40.5%
  13. 13 Kimi K3.1 Pro max 38.7%
  14. 14 Muse Spark 1.3 max 34.6%
  15. 15 Gemini 3.8 Flash high 33.3%
  16. 16 Kimi K3 max 28.3%
  17. 17 Muse Spark Open max 28.2%
  18. 18 GLM-5.3 max 25.1%
  19. 19 Grok 4.7 max 25%
  20. 20 DeepSeek-V4-Pro max 16.6%

Source: Official HLE-Diamond leaderboard

21 models. Scroll sideways for the rest.

  1. 77.9 Claude Fable 5.2
  2. 65.8 GPT-6 Astra
  3. 63.6 Gemini 4 Carbon
  4. 61.3 GPT-6.1 Sol
  5. 60.9 Claude Opus 5.5
  6. 56.9 Gemini 4 Argon
  7. 55.1 Claude Fable 5.1
  8. 43.3 Claude Sonnet 5.5
  9. 43.2 GPT-6 Sol
  10. 41.0 GPT-5.6 Sol
  11. 40.6 Muse Wonder
  12. 40.5 Claude Opus 5
  13. 38.7 Kimi K3.1 Pro
  14. 34.6 Muse Spark 1.3
  15. 33.3 Gemini 3.8 Flash
  16. 28.7 Inkling 2 Small
  17. 28.3 Kimi K3
  18. 28.2 Muse Spark Open
  19. 25.1 GLM-5.3
  20. 25.0 Grok 4.7
  21. 16.6 DeepSeek-V4-Pro
  1. 1 Claude Fable 5.2 max 77.9%
  2. 2 GPT-6 Astra max 65.8%
  3. 3 Gemini 4 Carbon high 63.6%
  4. 4 GPT-6.1 Sol max 61.3%
  5. 5 Claude Opus 5.5 max 60.9%
  6. 6 Gemini 4 Argon high 56.9%
  7. 7 Claude Fable 5.1 max 55.1%
  8. 8 Claude Sonnet 5.5 max 43.3%
  9. 9 GPT-6 Sol max 43.2%
  10. 10 GPT-5.6 Sol max 41%
  11. 11 Muse Wonder max 40.6%
  12. 12 Claude Opus 5 max 40.5%
  13. 13 Kimi K3.1 Pro max 38.7%
  14. 14 Muse Spark 1.3 max 34.6%
  15. 15 Gemini 3.8 Flash high 33.3%
  16. 16 Inkling 2 Small 28.7%
  17. 17 Kimi K3 max 28.3%
  18. 18 Muse Spark Open max 28.2%
  19. 19 GLM-5.3 max 25.1%
  20. 20 Grok 4.7 max 25%
  21. 21 DeepSeek-V4-Pro max 16.6%

Sources: Official HLE-Diamond leaderboard and labs’ model cards

#ModelScoreSettingDateSource
1 Claude Fable 5.2 77.9% max Nov 2026 Official leaderboard
2 GPT-6 Astra 65.8% max Sep 2026 Official leaderboard
3 Gemini 4 Carbon 63.6% high Oct 2026 Official leaderboard
4 GPT-6.1 Sol 61.3% max Sep 2026 Official leaderboard
5 Claude Opus 5.5 60.9% max Sep 2026 Official leaderboard
6 Gemini 4 Argon 56.9% high Sep 2026 Official leaderboard
7 Claude Fable 5.1 55.1% max Sep 2026 Official leaderboard
8 Claude Sonnet 5.5 43.3% max Sep 2026 Official leaderboard
9 GPT-6 Sol 43.2% max Sep 2026 Official leaderboard
10 GPT-5.6 Sol 41% max Jul 2026 Official leaderboard
11 Muse Wonder 40.6% max Oct 2026 Official leaderboard
12 Claude Opus 5 40.5% max Jul 2026 Official leaderboard
13 Kimi K3.1 Pro 38.7% max Oct 2026 Official leaderboard
14 Muse Spark 1.3 34.6% max Sep 2026 Official leaderboard
15 Gemini 3.8 Flash 33.3% high Sep 2026 Official leaderboard
16 Kimi K3 28.3% max Jul 2026 Official leaderboard
17 Muse Spark Open 28.2% max Oct 2026 Official leaderboard
18 GLM-5.3 25.1% max Aug 2026 Official leaderboard
19 Grok 4.7 25% max Sep 2026 Official leaderboard
20 DeepSeek-V4-Pro 16.6% max Apr 2026 Official leaderboard
#ModelScoreSettingDateSource
1 Claude Fable 5.2 77.9% max Nov 2026 Official leaderboard
2 GPT-6 Astra 65.8% max Sep 2026 Official leaderboard
3 Gemini 4 Carbon 63.6% high Oct 2026 Official leaderboard
4 GPT-6.1 Sol 61.3% max Sep 2026 Official leaderboard
5 Claude Opus 5.5 60.9% max Sep 2026 Official leaderboard
6 Gemini 4 Argon 56.9% high Sep 2026 Official leaderboard
7 Claude Fable 5.1 55.1% max Sep 2026 Official leaderboard
8 Claude Sonnet 5.5 43.3% max Sep 2026 Official leaderboard
9 GPT-6 Sol 43.2% max Sep 2026 Official leaderboard
10 GPT-5.6 Sol 41% max Jul 2026 Official leaderboard
11 Muse Wonder 40.6% max Oct 2026 Official leaderboard
12 Claude Opus 5 40.5% max Jul 2026 Official leaderboard
13 Kimi K3.1 Pro 38.7% max Oct 2026 Official leaderboard
14 Muse Spark 1.3 34.6% max Sep 2026 Official leaderboard
15 Gemini 3.8 Flash 33.3% high Sep 2026 Official leaderboard
16 Inkling 2 Small 28.7% Nov 2026 Lab model card
17 Kimi K3 28.3% max Jul 2026 Official leaderboard
18 Muse Spark Open 28.2% max Oct 2026 Official leaderboard
19 GLM-5.3 25.1% max Aug 2026 Official leaderboard
20 Grok 4.7 25% max Sep 2026 Official leaderboard
21 DeepSeek-V4-Pro 16.6% max Apr 2026 Official leaderboard

Labs report scores for 2 models in their cards. Switch the scores above to rank them together.

More effort adds a median 6 points

Models the leaderboard ran at two or more effort levels. We don’t have enough cost data here to say what the extra effort costs.

Lowest effort to highest, light to dark
Claude Fable 5.2
high max
77.9%
GPT-6 Astra
high max
65.8%
Gemini 4 Carbon
high
63.6%
GPT-6.1 Sol
high max
61.3%
Claude Opus 5.5
high max
60.9%
Gemini 4 Argon
high
56.9%
Claude Fable 5.1
high max
55.1%
Claude Sonnet 5.5
high max
43.3%
GPT-6 Sol
high max
43.2%
GPT-5.6 Sol
high max
41%
Muse Wonder
high max
40.6%
Claude Opus 5
high
40.5%

Source: Official HLE-Diamond leaderboard

ModelEffortHarnessScoreCost per taskOutput tokens
Claude Fable 5.2 max 77.9% 35,481
Claude Fable 5.2 high 74.3% 8,831
GPT-6 Astra max 65.8% 11,693
Gemini 4 Carbon high 63.6% 59,164
Gemini 4 Carbon max 63.6% 59,164
GPT-6.1 Sol max 61.3% 12,383
Claude Opus 5.5 max 60.9% 46,945
GPT-6 Astra high 59.9% 5,172
Gemini 4 Argon high 56.9% 26,087
Gemini 4 Argon max 56.9% 26,087
Claude Fable 5.1 max 55.1% 41,758
Claude Opus 5.5 high 54.6% 9,614
GPT-6.1 Sol high 53.2% 4,492
Claude Fable 5.1 high 51.6% 14,817
Claude Sonnet 5.5 max 43.3% 66,770
GPT-6 Sol max 43.2% 20,512
GPT-5.6 Sol max 41% 20,037
Muse Wonder max 40.6% 40,112
Claude Opus 5 max 40.5% 34,063
Kimi K3.1 Pro max 38.7% 37,725
Claude Opus 5 high 38.1% 19,656
Muse Wonder high 34.7% 16,125
Muse Spark 1.3 max 34.6% 32,818
Gemini 3.8 Flash high 33.3% 26,074
Gemini 3.8 Flash max 33.3% 26,074
Claude Sonnet 5.5 high 33.1% 8,584
GPT-6 Sol high 32.8% 4,597
GPT-5.6 Sol high 30.4% 5,912
Kimi K3.1 Pro high 29.5% 9,800
Kimi K3 max 28.3% 26,855
Muse Spark Open max 28.2% 22,779
GLM-5.3 max 25.1% 47,012
Grok 4.7 max 25% 57,366
Muse Spark Open high 24.9% 19,691
Muse Spark 1.3 high 24.6% 21,304
Grok 4.7 high 22.8% 43,244
GLM-5.3 high 22.3% 44,311
Kimi K3 high 21.7% 13,075
DeepSeek-V4-Pro max 16.6% 35,296
DeepSeek-V4-Pro high 13.4% 34,683

3 models have held number one on the official leaderboard since its release in September 2026 3 models have held number one with claims included since its release in September 2026

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

Anthropic OpenAI
Own leaderboard 3 leaders
Claude Fable 5.2 77.9%

Source: Official HLE-Diamond 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 Reported by the lab in its model card Best so far
0% 20% 40% 60% 80% 100% 2026 2027 Near the ceiling (85%) Claude Fable 5.2 GPT-6 Astra Claude Fable 5.1 GPT-5.6 Sol DeepSeek-V4-Pro 0% 20% 40% 60% 80% 100% 2026 2027 Near the ceiling (85%) Claude Fable 5.2 GPT-6 Astra

Sources: Official HLE-Diamond leaderboard and labs’ model cards

2 labs put it in a launch post in the last six months

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.

Meta
Thinking Machines
DateLaunch postScoreAs the post writes it
Nov 5, 2026 Inkling 2 Small 28.7 HLE-Diamond
Oct 15, 2026 Muse Spark Open 26.1 HLE-Diamond (no tools)

One lab claim next to the leaderboard

Each score a lab reported for its own model, beside the same model's best score on the leaderboard. Gaps mostly come from different harnesses, effort levels and task subsets. Every benchmark.

Model Lab says Board says Gap
Muse Spark Open 26.1% HLE-Diamond (no tools) 28.2% Leaderboard, max −2.1 pts

Versions

We switch the top row to each new version when it comes out. Open it for one row per version. An old version stays in play while people still test it, so whoever first takes it past 85% gets credit for closing it out.

OpenAI Anthropic Google DeepMind
HLE-Diamond 15 leaders
Claude Fable 5.2 77.9%
Humanity's Last Exam 12 leaders
GPT-6 Astra 54.8%
HLE-Diamond 3 leaders
Claude Fable 5.2 77.9%

Source: Official leaderboards

Replaces HLE-Rolling Replaces Humanity's Last Exam

More in Knowledge

All 121 in Knowledge
  • MMLU-Pro In use Harder 10-option version of MMLU with reasoning-focused questions across 14 subjects. Intern-S2-397B 89.8%
  • 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%
  • KMMLU-Pro In use Models answer multiple-choice questions taken from Korean National Professional Licensure exams. It tests professional knowledge used in Korean industry. Solar Pro 4 79.2%
  • HLE-Verified In use Verified and revised version of Humanity's Last Exam (1,811 items) with uncertain items removed. Seed2.0 Pro 73.6%