Benchmark Almanac

HMMT 2026

GPT-5.5 98.5% leads since April 2026
GPT-5.5 98.5% leads since April 2026
In use

Models solve the 33 final-answer problems from the February 2026 Harvard-MIT Mathematics Tournament. Scored by exact answer match.

An exam, not a dedicated benchmark. Top models score above 95%.

Released
February 2026
Kind
Competition problems with answers
Level
Competition
Scored
Checked automatically
Answers
Short answer
Tasks
All public
Strongest model tested
GPT-5.5 #20 on the capability index
Last in a launch post
November 2026
Last model added
November 2026
Scores refreshed
November 12th, 2026
31
Models scored on MathArena’s leaderboard
18
Launch posts list it, from 10 labs
7
System cards report it, from 6 labs

GPT-5.5 leads with 98.5% among models released by July 2026

Best score per model from MathArena’s 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.

GPT-5.5 leads with 98.5%, 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.

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:

31 models. Scroll sideways for the rest.

  1. 98.5 GPT-5.5
  2. 97.7 GPT-5.4
  3. 97.0 GPT-5.2
  4. 97.0 Kimi K3
  5. 96.2 Claude Opus 4.6
  6. 95.5 Gemini 3.5 Flash
  7. 95.5 Claude Opus 4.8
  8. 94.7 Gemini 3.1 Pro
  9. 94.7 Kimi K2.6
  10. 93.9 Claude Opus 4.7
  11. 93.9 DeepSeek-V4-Flash
  12. 93.9 DeepSeek-V4-Pro
  13. 92.4 GLM-5.2
  14. 89.4 Gemini 3 Flash
  15. 89.4 GLM-5.1
  16. 89.4 Gemini 3.6 Flash
  17. 87.9 Qwen3.5 397B-A17B
  18. 87.9 Step 3.7 Flash
  19. 87.1 Kimi K2.5
  20. 86.4 Gemini 3 Pro
  21. 86.4 Grok 4.1 Fast
  22. 86.4 Step 3.5 Flash
  23. 86.4 GLM-5
  24. 84.8 Nemotron 3 Super
  25. 84.1 DeepSeek-V3.2
  26. 81.8 Qwen3.5-35B-A3B
  27. 81.1 Qwen3.5-27B
  28. 78.8 Qwen3-30B-A3B-Thinking
  29. 71.2 Qwen3.5-9B
  30. 64.4 QED-Nano
  31. 53.0 Qwen3-4B-Thinking-2507
  1. 1 GPT-5.5 xhigh 98.5%
  2. 2 GPT-5.4 xhigh 97.7%
  3. 3 GPT-5.2 high 97%
  4. 4 Kimi K3 max 97%
  5. 5 Claude Opus 4.6 high 96.2%
  6. 6 Gemini 3.5 Flash high 95.5%
  7. 7 Claude Opus 4.8 max 95.5%
  8. 8 Gemini 3.1 Pro high 94.7%
  9. 9 Kimi K2.6 high 94.7%
  10. 10 Claude Opus 4.7 xhigh 93.9%
  11. 11 DeepSeek-V4-Flash max 93.9%
  12. 12 DeepSeek-V4-Pro max 93.9%
  13. 13 GLM-5.2 max 92.4%
  14. 14 Gemini 3 Flash high 89.4%
  15. 15 GLM-5.1 89.4%
  16. 16 Gemini 3.6 Flash 89.4%
  17. 17 Qwen3.5 397B-A17B 87.9%
  18. 18 Step 3.7 Flash high 87.9%
  19. 19 Kimi K2.5 high 87.1%
  20. 20 Gemini 3 Pro 86.4%
  21. 21 Grok 4.1 Fast reasoning 86.4%
  22. 22 Step 3.5 Flash 86.4%
  23. 23 GLM-5 86.4%
  24. 24 Nemotron 3 Super 84.8%
  25. 25 DeepSeek-V3.2 thinking 84.1%
  26. 26 Qwen3.5-35B-A3B 81.8%
  27. 27 Qwen3.5-27B 81.1%
  28. 28 Qwen3-30B-A3B-Thinking Jul 2025 78.8%
  29. 29 Qwen3.5-9B 71.2%
  30. 30 QED-Nano 64.4%
  31. 31 Qwen3-4B-Thinking-2507 53%

Source: MathArena’s leaderboard

45 models. Scroll sideways for the rest.

  1. 98.5 GPT-5.5
  2. 97.7 GPT-5.4
  3. 97.1 Qwen3.7-Max
  4. 97.0 GPT-5.2
  5. 97.0 Kimi K3
  6. 96.2 Claude Opus 4.6
  7. 95.8 Inkling 2 Small
  8. 95.5 Gemini 3.5 Flash
  9. 95.5 Claude Opus 4.8
  10. 95.2 DeepSeek-V4-Pro
  11. 94.8 DeepSeek-V4-Flash
  12. 94.7 Gemini 3.1 Pro
  13. 94.7 Kimi K2.6
  14. 93.9 Claude Opus 4.7
  15. 93.9 Solar Open 2
  16. 93.6 Intern-S2-397B
  17. 93.5 Ring-2.6-1T
  18. 92.9 Qwen3.7-Plus
  19. 92.5 GLM-5.2
  20. 90.2 Inkling-Small
  21. 89.4 Gemini 3 Flash
  22. 89.4 GLM-5.1
  23. 89.4 Gemini 3.6 Flash
  24. 87.9 Qwen3.5 397B-A17B
  25. 87.9 Step 3.7 Flash
  26. 87.8 Qwen 3.6 Plus
  27. 87.1 Kimi K2.5
  28. 86.4 Gemini 3 Pro
  29. 86.4 Grok 4.1 Fast
  30. 86.4 Step 3.5 Flash
  31. 86.4 GLM-5
  32. 84.9 MAI-Thinking-1
  33. 84.8 Nemotron 3 Super
  34. 84.3 Qwen3.6 27B
  35. 84.1 DeepSeek-V3.2
  36. 83.6 Qwen 3.6 35B-A3B
  37. 81.8 Qwen3.5-35B-A3B
  38. 81.3 Spark-X2.6-4B
  39. 81.1 Qwen3.5-27B
  40. 78.8 Qwen3-30B-A3B-Thinking
  41. 78.4 K-EXAONE 2.0
  42. 71.2 Qwen3.5-9B
  43. 65.9 Solar Pro 3 (March 2026 update)
  44. 64.4 QED-Nano
  45. 53.0 Qwen3-4B-Thinking-2507
  1. 1 GPT-5.5 xhigh 98.5%
  2. 2 GPT-5.4 xhigh 97.7%
  3. 3 Qwen3.7-Max 97.1%
  4. 4 GPT-5.2 high 97%
  5. 5 Kimi K3 max 97%
  6. 6 Claude Opus 4.6 high 96.2%
  7. 7 Inkling 2 Small 95.8%
  8. 8 Gemini 3.5 Flash high 95.5%
  9. 9 Claude Opus 4.8 max 95.5%
  10. 10 DeepSeek-V4-Pro 95.2%
  11. 11 DeepSeek-V4-Flash 94.8%
  12. 12 Gemini 3.1 Pro high 94.7%
  13. 13 Kimi K2.6 high 94.7%
  14. 14 Claude Opus 4.7 xhigh 93.9%
  15. 15 Solar Open 2 93.9%
  16. 16 Intern-S2-397B 93.6%
  17. 17 Ring-2.6-1T 93.5%
  18. 18 Qwen3.7-Plus 92.9%
  19. 19 GLM-5.2 92.5%
  20. 20 Inkling-Small 90.2%
  21. 21 Gemini 3 Flash high 89.4%
  22. 22 GLM-5.1 89.4%
  23. 23 Gemini 3.6 Flash 89.4%
  24. 24 Qwen3.5 397B-A17B 87.9%
  25. 25 Step 3.7 Flash high 87.9%
  26. 26 Qwen 3.6 Plus 87.8%
  27. 27 Kimi K2.5 high 87.1%
  28. 28 Gemini 3 Pro 86.4%
  29. 29 Grok 4.1 Fast reasoning 86.4%
  30. 30 Step 3.5 Flash 86.4%
  31. 31 GLM-5 86.4%
  32. 32 MAI-Thinking-1 84.9%
  33. 33 Nemotron 3 Super 84.8%
  34. 34 Qwen3.6 27B 84.3%
  35. 35 DeepSeek-V3.2 thinking 84.1%
  36. 36 Qwen 3.6 35B-A3B 83.6%
  37. 37 Qwen3.5-35B-A3B 81.8%
  38. 38 Spark-X2.6-4B 81.3%
  39. 39 Qwen3.5-27B 81.1%
  40. 40 Qwen3-30B-A3B-Thinking Jul 2025 78.8%
  41. 41 K-EXAONE 2.0 78.4%
  42. 42 Qwen3.5-9B 71.2%
  43. 43 Solar Pro 3 (March 2026 update) 65.9%
  44. 44 QED-Nano 64.4%
  45. 45 Qwen3-4B-Thinking-2507 53%

Sources: MathArena’s leaderboard and labs’ model cards

#ModelScoreSettingDateSource
1 GPT-5.5 98.5% xhigh Apr 2026 Official leaderboard
2 GPT-5.4 97.7% xhigh Mar 2026 Official leaderboard
3 GPT-5.2 97% high Dec 2025 Official leaderboard
4 Kimi K3 97% max Jul 2026 Official leaderboard
5 Claude Opus 4.6 96.2% high Feb 2026 Official leaderboard
6 Gemini 3.5 Flash 95.5% high May 2026 Official leaderboard
7 Claude Opus 4.8 95.5% max May 2026 Official leaderboard
8 Gemini 3.1 Pro 94.7% high Feb 2026 Official leaderboard
9 Kimi K2.6 94.7% high Apr 2026 Official leaderboard
10 Claude Opus 4.7 93.9% xhigh Apr 2026 Official leaderboard
11 DeepSeek-V4-Flash 93.9% max Apr 2026 Official leaderboard
12 DeepSeek-V4-Pro 93.9% max Apr 2026 Official leaderboard
13 GLM-5.2 92.4% max Jun 2026 Official leaderboard
14 Gemini 3 Flash 89.4% high Dec 2025 Official leaderboard
15 GLM-5.1 89.4% Apr 2026 Official leaderboard
16 Gemini 3.6 Flash 89.4% Jul 2026 Official leaderboard
17 Qwen3.5 397B-A17B 87.9% Feb 2026 Official leaderboard
18 Step 3.7 Flash 87.9% high May 2026 Official leaderboard
19 Kimi K2.5 87.1% high Jan 2026 Official leaderboard
20 Gemini 3 Pro 86.4% Nov 2025 Official leaderboard
21 Grok 4.1 Fast 86.4% reasoning Nov 2025 Official leaderboard
22 Step 3.5 Flash 86.4% Feb 2026 Official leaderboard
23 GLM-5 86.4% Feb 2026 Official leaderboard
24 Nemotron 3 Super 84.8% Mar 2026 Official leaderboard
25 DeepSeek-V3.2 84.1% thinking Dec 2025 Official leaderboard
26 Qwen3.5-35B-A3B 81.8% Feb 2026 Official leaderboard
27 Qwen3.5-27B 81.1% Feb 2026 Official leaderboard
28 Qwen3-30B-A3B-Thinking Jul 2025 78.8% Jul 2025 Official leaderboard
29 Qwen3.5-9B 71.2% Feb 2026 Official leaderboard
30 QED-Nano 64.4% Feb 2026 Official leaderboard
31 Qwen3-4B-Thinking-2507 53% Aug 2025 Official leaderboard
#ModelScoreSettingDateSource
1 GPT-5.5 98.5% xhigh Apr 2026 Official leaderboard
2 GPT-5.4 97.7% xhigh Mar 2026 Official leaderboard
3 Qwen3.7-Max 97.1% May 2026 Lab model card
4 GPT-5.2 97% high Dec 2025 Official leaderboard
5 Kimi K3 97% max Jul 2026 Official leaderboard
6 Claude Opus 4.6 96.2% high Feb 2026 Official leaderboard
7 Inkling 2 Small 95.8% Nov 2026 Lab model card
8 Gemini 3.5 Flash 95.5% high May 2026 Official leaderboard
9 Claude Opus 4.8 95.5% max May 2026 Official leaderboard
10 DeepSeek-V4-Pro 95.2% Apr 2026 Lab model card
11 DeepSeek-V4-Flash 94.8% Apr 2026 Lab model card
12 Gemini 3.1 Pro 94.7% high Feb 2026 Official leaderboard
13 Kimi K2.6 94.7% high Apr 2026 Official leaderboard
14 Claude Opus 4.7 93.9% xhigh Apr 2026 Official leaderboard
15 Solar Open 2 93.9% Jul 2026 Lab model card
16 Intern-S2-397B 93.6% Sep 2026 Lab model card
17 Ring-2.6-1T 93.5% Jun 2026 Lab model card
18 Qwen3.7-Plus 92.9% Jun 2026 Lab model card
19 GLM-5.2 92.5% Jun 2026 Lab model card
20 Inkling-Small 90.2% Jul 2026 Lab model card
21 Gemini 3 Flash 89.4% high Dec 2025 Official leaderboard
22 GLM-5.1 89.4% Apr 2026 Official leaderboard
23 Gemini 3.6 Flash 89.4% Jul 2026 Official leaderboard
24 Qwen3.5 397B-A17B 87.9% Feb 2026 Official leaderboard
25 Step 3.7 Flash 87.9% high May 2026 Official leaderboard
26 Qwen 3.6 Plus 87.8% Apr 2026 Lab model card
27 Kimi K2.5 87.1% high Jan 2026 Official leaderboard
28 Gemini 3 Pro 86.4% Nov 2025 Official leaderboard
29 Grok 4.1 Fast 86.4% reasoning Nov 2025 Official leaderboard
30 Step 3.5 Flash 86.4% Feb 2026 Official leaderboard
31 GLM-5 86.4% Feb 2026 Official leaderboard
32 MAI-Thinking-1 84.9% Jun 2026 Lab model card
33 Nemotron 3 Super 84.8% Mar 2026 Official leaderboard
34 Qwen3.6 27B 84.3% Apr 2026 Lab model card
35 DeepSeek-V3.2 84.1% thinking Dec 2025 Official leaderboard
36 Qwen 3.6 35B-A3B 83.6% Apr 2026 Lab model card
37 Qwen3.5-35B-A3B 81.8% Feb 2026 Official leaderboard
38 Spark-X2.6-4B 81.3% Oct 2026 Lab model card
39 Qwen3.5-27B 81.1% Feb 2026 Official leaderboard
40 Qwen3-30B-A3B-Thinking Jul 2025 78.8% Jul 2025 Official leaderboard
41 K-EXAONE 2.0 78.4% Jul 2026 Lab model card
42 Qwen3.5-9B 71.2% Feb 2026 Official leaderboard
43 Solar Pro 3 (March 2026 update) 65.9% Mar 2026 Lab model card
44 QED-Nano 64.4% Feb 2026 Official leaderboard
45 Qwen3-4B-Thinking-2507 53% Aug 2025 Official leaderboard

Labs report scores for 19 models in their cards. Switch the scores above to rank them together.

The best score, 98.5%, costs $0.26 a task

Runs on the cost frontier score higher than any run that's cheaper. DeepSeek-V4-Flash at max comes within 4.5 points of the best for $0.01 a task, 17 times cheaper. The costs are the leaderboard's own estimates, so compare them only within this benchmark.

xAI OpenAI Qwen Moonshot AI DeepSeek Google DeepMind Cost frontier One model at each effort level
0% 20% 40% 60% 80% 100% $0.001 $0.01 $0.10 $1.00 Cost per task, log scale GPT-5.5, xhigh Kimi K2.6, high DeepSeek-V4-Flash, max Grok 4.1 Fast, reasoning Qwen3.5-9B 0% 20% 40% 60% 80% 100% $0.001 $0.01 $0.10 $1.00 Cost per task, log scale GPT-5.5, xhigh Grok 4.1 Fast, reasoning

Source: MathArena’s leaderboard

ModelEffortHarnessScoreCost per taskOutput tokens
GPT-5.5 xhigh 98.5% $0.26 8,496
GPT-5.4 xhigh 97.7% $0.22 14,538
GPT-5.2 high 97% $0.19 13,709
Kimi K3 max 97% $0.22 14,694
Claude Opus 4.6 high 96.2% $0.64 25,758
Gemini 3.5 Flash high 95.5% $0.15 16,121
Claude Opus 4.8 max 95.5% $0.76 30,441
Gemini 3.1 Pro high 94.7% $0.20 16,761
Kimi K2.6 high 94.7% $0.13 33,563
Claude Opus 4.7 xhigh 93.9% $0.56 22,279
DeepSeek-V4-Flash max 93.9% $0.01 54,365
DeepSeek-V4-Pro max 93.9% $0.14 40,696
GLM-5.2 max 92.4% $0.10 23,293
Gemini 3 Flash high 89.4% $0.07 21,896
GLM-5.1 89.4% $0.13 39,645
Gemini 3.6 Flash 89.4% $0.10 13,542
Qwen3.5 397B-A17B 87.9% $0.09 24,189
Step 3.7 Flash high 87.9% $0.02 81,069
Kimi K2.5 high 87.1% $0.09 28,765
Gemini 3 Pro 86.4% $0.19 15,502
Grok 4.1 Fast reasoning 86.4% $0.007 13,846
Step 3.5 Flash 86.4% $0.02 60,004
GLM-5 86.4% $0.11 33,206
Nemotron 3 Super 84.8% 45,773
DeepSeek-V3.2 thinking 84.1% $0.01 24,288
Qwen3.5-35B-A3B 81.8% $0.06 42,716
Qwen3.5-27B 81.1% $0.06 37,594
Qwen3-30B-A3B-Thinking Jul 2025 78.8% $0.007 24,319
Qwen3.5-9B 71.2% $0.006 40,607
QED-Nano 64.4% 57,709
Qwen3-4B-Thinking-2507 53% $0.008 27,600

3 models have held number one on MathArena’s leaderboard since its release in February 2026 3 models have held number one with claims included since its release in February 2026

Lab claims count from the day the card came out, independent runs from the model’s release. We draw one row each for MathArena’s leaderboard and what labs claim in their cards.

OpenAI Upstage Qwen Moonshot AI DeepSeek
MathArena leaderboard Passed 85% in Feb 2026, by GPT-5.2
GPT-5.5 98.5%
Lab claims Passed 85% in Apr 2026, by Qwen 3.6 Plus
Qwen3.7-Max 97.1%

Sources: MathArena’s leaderboard and labs’ model cards

Gemini 3 Pro on the official leaderboard passed 85% in November 2025

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

On MathArena’s leaderboard Reported by the lab in its model card Best so far
0% 20% 40% 60% 80% 100% 2026 2027 Near the ceiling (85%) GPT-5.5 GPT-5.2 Gemini 3 Pro Qwen3-30B-A3B-Thinking 0% 20% 40% 60% 80% 100% 2026 2027 Near the ceiling (85%) GPT-5.5 Gemini 3 Pro

Sources: MathArena’s leaderboard and labs’ model cards

8 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.

Upstage
Qwen
Z.ai
Moonshot AI
DeepSeek
Microsoft
Thinking Machines
LG AI Research
Shanghai AI Lab
iFlytek
DateLaunch postScoreAs the post writes it
Nov 5, 2026 Inkling 2 Small 95.8 HMMT Feb 2026, 95.8%
Oct 22, 2026 Spark-X2.6-4B 81.3 HMMT Feb 26
Sep 13, 2026 Intern-S2-397B 93.6 HMMT-2026
Jul 31, 2026 K-EXAONE 2.0 78.4 HMMT Feb 2026
Jul 30, 2026 Inkling-Small 90.2 HMMT Feb 2026
Jul 22, 2026 Solar Open 2 93.9 HMMT2602 (MathArena)
Jun 16, 2026 GLM-5.2 92.5 HMMT Feb. 2026
Jun 2, 2026 MAI-Thinking-1 84.9 HMMT Feb 2026
Jun 1, 2026 Qwen3.7-Plus 92.9 HMMT 2026 Feb
May 20, 2026 Qwen3.7-Max 97.1 HMMT 2026 Feb
Apr 24, 2026 DeepSeek-V4-Flash 94.8 HMMT 2026 Feb (Pass@1), V4-Flash Max
Apr 24, 2026 DeepSeek-V4-Pro 95.2 HMMT 2026 Feb (Pass@1)
Apr 22, 2026 Qwen3.6 27B 84.3 HMMT Feb 26
Apr 20, 2026 Kimi K2.6 92.7 HMMT 2026 (Feb)
Apr 15, 2026 Qwen 3.6 35B-A3B 83.6 HMMT Feb 26
Apr 7, 2026 GLM-5.1 82.6 HMMT Feb. 2026
Apr 2, 2026 Qwen 3.6 Plus 87.8 HMMT Feb 26
Mar 24, 2026 Solar Pro 3 (March 2026 update) 65.9 HMMT'26

7 system cards report it, from 6 labs

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
Aug 5, 2026 K-EXAONE 2.0 technical report 78.4 HMMT Feb 2026 (Table 6, Reasoning mode) Capabilities
Jul 30, 2026 Inkling-Small model card 90.2 HMMT Feb 2026 (5. Evaluations table) Capabilities
Jul 22, 2026 Solar Open 2 technical report 93.9 HMMT2602, MathArena set (Table 3) Capabilities
Jun 13, 2026 Ring-2.6-1T technical report 93.5 HMMT-Feb26 (Avg@64), xhigh (Table 6). High gives 67.80 Capabilities
Jun 2, 2026 MAI-Thinking-1 technical report 84.9 HMMT Feb 2026, pass@1, 256k max output tokens (Table 11) Capabilities
Apr 26, 2026 DeepSeek-V4-Pro technical report 95.2 HMMT 2026 Feb (Pass@1), DS-V4-Pro Max (Table 6) Capabilities
Apr 26, 2026 DeepSeek-V4-Flash technical report 94.8 HMMT 2026 Feb (Pass@1), DeepSeek-V4-Flash Max (Table 7) Capabilities

The lab's number comes out ahead in 2 of 4 pairs that differ

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. 1 of them match, which usually means one side copied the other. Every benchmark.

Model Lab says Board says Gap
GLM-5.1 82.6% HMMT Feb. 2026 89.4% Leaderboard −6.8 pts
Kimi K2.6 92.7% HMMT 2026 (Feb) 94.7% Leaderboard, high −2.0 pts
DeepSeek-V4-Pro 95.2% HMMT 2026 Feb (Pass@1) 93.9% Leaderboard, max +1.3 pts
DeepSeek-V4-Flash 94.8% HMMT 2026 Feb (Pass@1), V4-Flash Max 93.9% Leaderboard, max +0.9 pts
GLM-5.2 92.5% HMMT Feb. 2026 92.4% Leaderboard, max Same

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.

Microsoft DeepSeek xAI OpenAI
HMMT 2026 Passed 85% in Feb 2026, by GPT-5.2
GPT-5.5 98.5%
HMMT 2025 Passed 85% in Jul 2025, by Grok 4 Heavy
GPT-5 100%
HMMT 2026 Passed 85% in Feb 2026, by GPT-5.2
GPT-5.5 98.5%

Sources: Official leaderboards and labs’ model cards

Replaces HMMT 2025

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%
  • 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%
  • FrontierMath Tiers 1-3 v2 In use Models solve 295 unpublished math problems from undergraduate to advanced graduate level and submit answers that code checks automatically. Scored by share correct. Claude Fable 5.2 95.1%