Benchmark Almanac

PerceptionBench (Moonshot)

GPT-5.6 Sol 59.7% leads since July 2026
Muse Ember 80.6% leads since November 2026
In use

Moonshot in-house benchmark of atomic visual perception skills. Scoring details unpublished.

Lab-created in-house eval (Moonshot AI). Not the same as other public benchmarks with this name.

Made by
Moonshot AI
Released
July 2026
Kind
General visual questions
Level
Everyday
Scored
Checked automatically
Answers
Short answer
Tasks
Kept private
Strongest model tested
Claude Fable 5 #11 on the capability index
Last in a launch post
November 2026
Last model added
November 2026
Scores refreshed
November 12th, 2026
16
Models scored on its own leaderboard
5
Launch posts list it, from 4 labs
2
System cards report it, from 2 labs

GPT-5.6 Sol leads with 59.7% among models released by July 2026

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.

Muse Ember leads with 80.6%, 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:

16 models. Scroll sideways for the rest.

  1. 59.7 GPT-5.6 Sol
  2. 58.5 Kimi K3
  3. 57.2 Claude Fable 5
  4. 56.2 Gemini 3.1 Pro
  5. 55.8 GPT-5.5
  6. 55.0 Seed2.1 Pro
  7. 52.0 Gemini 3.5 Flash
  8. 51.1 Qwen3.7-Plus
  9. 47.5 Qwen3.5 397B-A17B
  10. 47.2 Claude Opus 4.8
  11. 42.6 Kimi K2.6
  12. 41.0 Grok 4.5
  13. 40.7 Gemma 4 31B IT
  14. 39.6 GLM-5V-Turbo
  15. 33.1 MiniMax-M3
  16. 32.5 GLM-4.6V
  1. 1 GPT-5.6 Sol 59.7%
  2. 2 Kimi K3 58.5%
  3. 3 Claude Fable 5 57.2%
  4. 4 Gemini 3.1 Pro 56.2%
  5. 5 GPT-5.5 55.8%
  6. 6 Seed2.1 Pro 55%
  7. 7 Gemini 3.5 Flash 52%
  8. 8 Qwen3.7-Plus 51.1%
  9. 9 Qwen3.5 397B-A17B 47.5%
  10. 10 Claude Opus 4.8 47.2%
  11. 11 Kimi K2.6 42.6%
  12. 12 Grok 4.5 41%
  13. 13 Gemma 4 31B IT 40.7%
  14. 14 GLM-5V-Turbo 39.6%
  15. 15 MiniMax-M3 33.1%
  16. 16 GLM-4.6V 32.5%

Source: Official PerceptionBench (Moonshot) leaderboard

20 models. Scroll sideways for the rest.

  1. 80.6 Muse Ember
  2. 68.3 Kimi K3.1 Pro
  3. 64.7 Inkling 2 Small
  4. 63.5 Qwen 3.8 Max
  5. 59.7 GPT-5.6 Sol
  6. 58.5 Kimi K3
  7. 57.2 Claude Fable 5
  8. 56.2 Gemini 3.1 Pro
  9. 55.8 GPT-5.5
  10. 55.0 Seed2.1 Pro
  11. 52.0 Gemini 3.5 Flash
  12. 51.1 Qwen3.7-Plus
  13. 47.5 Qwen3.5 397B-A17B
  14. 47.2 Claude Opus 4.8
  15. 42.6 Kimi K2.6
  16. 41.0 Grok 4.5
  17. 40.7 Gemma 4 31B IT
  18. 39.6 GLM-5V-Turbo
  19. 33.1 MiniMax-M3
  20. 32.5 GLM-4.6V
  1. 1 Muse Ember 80.6%
  2. 2 Kimi K3.1 Pro 68.3%
  3. 3 Inkling 2 Small 64.7%
  4. 4 Qwen 3.8 Max 63.5%
  5. 5 GPT-5.6 Sol 59.7%
  6. 6 Kimi K3 58.5%
  7. 7 Claude Fable 5 57.2%
  8. 8 Gemini 3.1 Pro 56.2%
  9. 9 GPT-5.5 55.8%
  10. 10 Seed2.1 Pro 55%
  11. 11 Gemini 3.5 Flash 52%
  12. 12 Qwen3.7-Plus 51.1%
  13. 13 Qwen3.5 397B-A17B 47.5%
  14. 14 Claude Opus 4.8 47.2%
  15. 15 Kimi K2.6 42.6%
  16. 16 Grok 4.5 41%
  17. 17 Gemma 4 31B IT 40.7%
  18. 18 GLM-5V-Turbo 39.6%
  19. 19 MiniMax-M3 33.1%
  20. 20 GLM-4.6V 32.5%

Sources: Labs’ model cards and official PerceptionBench (Moonshot) leaderboard

#ModelScoreSettingDateSource
1 GPT-5.6 Sol 59.7% Jul 2026 Official leaderboard
2 Kimi K3 58.5% Jul 2026 Official leaderboard
3 Claude Fable 5 57.2% Jun 2026 Official leaderboard
4 Gemini 3.1 Pro 56.2% Feb 2026 Official leaderboard
5 GPT-5.5 55.8% Apr 2026 Official leaderboard
6 Seed2.1 Pro 55% Jun 2026 Official leaderboard
7 Gemini 3.5 Flash 52% May 2026 Official leaderboard
8 Qwen3.7-Plus 51.1% Jun 2026 Official leaderboard
9 Qwen3.5 397B-A17B 47.5% Feb 2026 Official leaderboard
10 Claude Opus 4.8 47.2% May 2026 Official leaderboard
11 Kimi K2.6 42.6% Apr 2026 Official leaderboard
12 Grok 4.5 41% Jul 2026 Official leaderboard
13 Gemma 4 31B IT 40.7% Apr 2026 Official leaderboard
14 GLM-5V-Turbo 39.6% Apr 2026 Official leaderboard
15 MiniMax-M3 33.1% Jun 2026 Official leaderboard
16 GLM-4.6V 32.5% Dec 2025 Official leaderboard
#ModelScoreSettingDateSource
1 Muse Ember 80.6% Nov 2026 Lab model card
2 Kimi K3.1 Pro 68.3% Oct 2026 Lab model card
3 Inkling 2 Small 64.7% Nov 2026 Lab model card
4 Qwen 3.8 Max 63.5% Aug 2026 Lab model card
5 GPT-5.6 Sol 59.7% Jul 2026 Official leaderboard
6 Kimi K3 58.5% Jul 2026 Official leaderboard
7 Claude Fable 5 57.2% Jun 2026 Official leaderboard
8 Gemini 3.1 Pro 56.2% Feb 2026 Official leaderboard
9 GPT-5.5 55.8% Apr 2026 Official leaderboard
10 Seed2.1 Pro 55% Jun 2026 Official leaderboard
11 Gemini 3.5 Flash 52% May 2026 Official leaderboard
12 Qwen3.7-Plus 51.1% Jun 2026 Official leaderboard
13 Qwen3.5 397B-A17B 47.5% Feb 2026 Official leaderboard
14 Claude Opus 4.8 47.2% May 2026 Official leaderboard
15 Kimi K2.6 42.6% Apr 2026 Official leaderboard
16 Grok 4.5 41% Jul 2026 Official leaderboard
17 Gemma 4 31B IT 40.7% Apr 2026 Official leaderboard
18 GLM-5V-Turbo 39.6% Apr 2026 Official leaderboard
19 MiniMax-M3 33.1% Jun 2026 Official leaderboard
20 GLM-4.6V 32.5% Dec 2025 Official leaderboard

Labs report scores for 5 models in their cards. Switch the scores above to rank them together.

2 models have held number one on the official leaderboard since its release in July 2026 5 models have held number one with claims included since its release in July 2026

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

Anthropic OpenAI Moonshot AI Qwen Meta
Own leaderboard Not tested since Jul 2026
GPT-5.6 Sol 59.7%
Lab claims 4 leaders
Muse Ember 80.6%

Sources: Official PerceptionBench (Moonshot) leaderboard and 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.

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%) Muse Ember Kimi K3.1 Pro Qwen 3.8 Max Claude Fable 5 Gemini 3.1 Pro Qwen3.5 397B-A17B GLM-4.6V 0% 20% 40% 60% 80% 100% 2026 2027 Near the ceiling (85%) Muse Ember Kimi K3.1 Pro

Sources: Official PerceptionBench (Moonshot) leaderboard and labs’ model cards

4 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.

Moonshot AI
Qwen
Thinking Machines
Meta
DateLaunch postScoreAs the post writes it
Nov 9, 2026 Muse Ember 80.6 PerceptionBench with tools, Muse Ember max reasoning
Nov 5, 2026 Inkling 2 Small 64.7 PerceptionBench
Oct 24, 2026 Kimi K3.1 Pro 68.3 PerceptionBench
Aug 3, 2026 Qwen 3.8 Max 63.5 PerceptionBench
Jul 16, 2026 Kimi K3 58.5 PerceptionBench

2 system cards report it, from 2 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
Nov 9, 2026 Muse Ember technical report 80.6 PerceptionBench with tools, Muse Ember max reasoning Capabilities
Jul 27, 2026 Kimi K3 technical report 58.5 PerceptionBench (Table 2) Capabilities

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

Model Lab says Board says Gap
Kimi K3 58.5% PerceptionBench 58.5% Leaderboard Same

More in Vision

All 281 in Vision
  • MMMU In use 11.5K college-level multimodal questions across 30 subjects. Multiple-choice and open accuracy. GPT-5.1 85.4%
  • MMMU-Pro In use Harder MMMU: college-level multimodal questions with more options and vision-only inputs to remove text shortcuts. GPT-5.6 Sol 84.6%
  • CharXiv In use Chart understanding on real arXiv figures. Reasoning questions require synthesizing information from complex charts. Claude Fable 5 93.5%
  • MATH-Vision (MathVision) In use 3,040 competition math problems with visual context. Answer accuracy. Qwen 3.8 Max 97.7%
  • MMStar In use Models answer 1,500 human-curated image questions that cannot be solved without the image, across 6 core capabilities. Scored by accuracy. Qwen 3.8 Max 85.9%
  • ChartQA In use Models answer human-written and generated questions about chart images that need visual and arithmetic reasoning. Scored by relaxed accuracy with a 5 percent numeric tolerance. Command A Vision 90.9%