Benchmark Almanac

FretBench

Gemini 3.1 Pro 100% leads since March 2026
Not in model cards

Models read guitar tablature in four tunings and name notes from string positions and fret numbers. The grader compares their answers with an answer key.

The maker ranks 18 models in 21 configurations on a 239-case dataset. The March release used 182 cases and had a grading error with sharp notes.

Made by
Jaiden Capra
Released
March 2026
Kind
Language reasoning
Level
School
Scored
Checked automatically
Answers
Short answer
Tasks
Public, plus a private test set
Measures
Capability
Subject
Arts
Language
English
In and out
Text → Text
Interaction
Single turn
Run by
A host
Strongest model tested
GPT-5.4 #28 on the capability index
Last model added
April 2026
Scores refreshed
November 20th, 2026
18
Models scored on its own leaderboard

Gemini 3.1 Pro leads with 100% among models released by April 2026

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. Every run is in the next chart.

The newest model with a score here came out in April 2026, 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 3.1 Pro 100%
  2. 2 DeepSeek-V3.2-Speciale 99.6%
  3. 3 Kimi K2.5 Reasoning 99.6%
  4. 4 Qwen3.5-Plus 99.6%
  5. 5 Qwen3.5-Flash 98.3%
  6. 6 Claude Opus 4.7 87.2%
  7. 7 MiniMax-M2.5 84.9%
  8. 8 GPT-5.4 63.2%
  9. 9 Claude Opus 4.6 59.8%
  10. 10 Gemma 4 31B IT 51.7%
  11. 11 Gemini 3.1 Flash-Lite 38.5%
  12. 12 Gemma 4 26B A4B 36.2%
  13. 13 Mistral Large 24.7%
  14. 14 Llama 3.3 70B 24.7%
  15. 15 Claude Sonnet 4.6 20.5%
  16. 16 DeepSeek-V3.2 20.1%
  17. 17 Claude Haiku 4.5 17.6%
  18. 18 Llama 4 Scout 13.8%

Source: Official FretBench leaderboard

#ModelScoreSettingReleasedRun onSource
1 Gemini 3.1 Pro 100% Feb 2026 Apr 2026 Official leaderboard
2 DeepSeek-V3.2-Speciale 99.6% Dec 2025 Mar 2026 Official leaderboard
3 Kimi K2.5 99.6% Reasoning Jan 2026 Mar 2026 Official leaderboard
4 Qwen3.5-Plus 99.6% Feb 2026 Mar 2026 Official leaderboard
5 Qwen3.5-Flash 98.3% Feb 2026 Mar 2026 Official leaderboard
6 Claude Opus 4.7 87.2% Apr 2026 Apr 2026 Official leaderboard
7 MiniMax-M2.5 84.9% Feb 2026 Mar 2026 Official leaderboard
8 GPT-5.4 63.2% Mar 2026 Mar 2026 Official leaderboard
9 Claude Opus 4.6 59.8% Feb 2026 Mar 2026 Official leaderboard
10 Gemma 4 31B IT 51.7% Apr 2026 Apr 2026 Official leaderboard
11 Gemini 3.1 Flash-Lite 38.5% Mar 2026 Mar 2026 Official leaderboard
12 Gemma 4 26B A4B 36.2% Apr 2026 Apr 2026 Official leaderboard
13 Mistral Large 24.7% Feb 2024 Mar 2026 Official leaderboard
14 Llama 3.3 70B 24.7% Dec 2024 Mar 2026 Official leaderboard
15 Claude Sonnet 4.6 20.5% Feb 2026 Mar 2026 Official leaderboard
16 DeepSeek-V3.2 20.1% Dec 2025 Mar 2026 Official leaderboard
17 Claude Haiku 4.5 17.6% Oct 2025 Mar 2026 Official leaderboard
18 Llama 4 Scout 13.8% Apr 2025 Mar 2026 Official leaderboard

Rankings by part

We read 4 parts from the benchmark’s own leaderboard, each ranking models on one part of the test, such as Drop D, Drop Db and Half-Step Down. DeepSeek-V3.2-Speciale leads 3 of them, and Gemini 3.1 Pro leads the other one. Arrows show how far a model moved from its overall rank among the models we track.

Drop D

18 models we track have a score here.

  1. 1 DeepSeek-V3.2-Speciale ↑1 100%
  2. 2 Kimi K2.5 ↑1 100%
  3. 3 Qwen3.5-Plus ↑1 100%
  4. 4 Gemini 3.1 Pro ↓3 100%
  5. 5 Qwen3.5-Flash 100%
  6. 6 Claude Opus 4.7 87.8%
  7. 7 MiniMax-M2.5 80%
  8. 8 GPT-5.4 68.9%
  9. 9 Gemma 4 31B IT ↑1 58.4%
  10. 10 Gemini 3.1 Flash-Lite ↑1 53.3%

The best score, 100%, costs $1.30 for the full run

Runs on the cost frontier score higher than any run that's cheaper. Qwen3.5-Flash comes within 1.7 points of the best for $0.23 for the full run, 6 times cheaper. The costs are the leaderboard's own estimates, so compare them only within this benchmark.

Meta DeepSeek MiniMax Google DeepMind Qwen Cost frontier One model at each effort level
0% 20% 40% 60% 80% 100% $0.01 $0.10 $1.00 $10 Cost of the full run, log scale Gemini 3.1 Pro DeepSeek-V3.2-Speciale MiniMax-M2.5 Gemma 4 31B IT Gemini 3.1 Flash-Lite Llama 4 Scout 0% 20% 40% 60% 80% 100% $0.01 $0.10 $1.00 $10 Cost of the full run, log scale Gemini 3.1 Pro MiniMax-M2.5

Source: Official FretBench leaderboard

ModelEffortHarnessScoreCost of the full runOutput tokens
Gemini 3.1 Pro 100% $1.30
DeepSeek-V3.2-Speciale 99.6% $0.42
DeepSeek-V3.2-Speciale Reasoning 99.6% $0.44
Kimi K2.5 Reasoning 99.6% $0.63
Kimi K2.5 99.6% $0.65
Qwen3.5-Plus 99.6% $0.61
Qwen3.5-Flash 98.3% $0.23
Claude Opus 4.7 87.2% $2.38
MiniMax-M2.5 84.9% $0.16
MiniMax-M2.5 Reasoning 82.8% $0.16
GPT-5.4 63.2% $0.32
Claude Opus 4.6 59.8% $0.75
Gemma 4 31B IT 51.7% $0.03
Gemini 3.1 Flash-Lite 38.5% $0.03
Gemma 4 26B A4B 36.2% $0.02
Mistral Large 24.7% $0.05
Llama 3.3 70B 24.7% $0.03
Claude Sonnet 4.6 20.5% $0.59
DeepSeek-V3.2 20.1% $0.03
Claude Haiku 4.5 17.6% $0.17
Llama 4 Scout 13.8% $0.02

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 Passed 85% in Mar 2026, by Gemini 3.1 Pro

Source: Official FretBench leaderboard

DeepSeek-V3.2-Speciale on the official leaderboard passed 85% in December 2025

Models released before it came out already scored that high. 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 2026 Near the ceiling (85%) Gemini 3.1 Pro Mistral Large 0% 20% 40% 60% 80% 100% 2024 2025 2026 Near the ceiling (85%) Gemini 3.1 Pro Mistral Large

Source: Official FretBench 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

All 8 checks pass. Every benchmark

Catalog record 2 pass
  • Pass Task access Public tasks, plus a private test set.
  • Pass Confidence Checked against a primary source.
Scores 2 pass 3 notes
  • Pass Independent runs Scores from the official leaderboard (18 entries).
  • Pass Models scored 18 models we track.
  • Note Newest score The newest came 7 months ago, in April 2026, for Claude Opus 4.7. That’s expected for a saturated test.
  • Note Frontier models None of the top 10 has a score, which is fine for a retired test. The strongest tested is GPT-5.4 (#28).
  • Note Headroom Saturated. The best is 100%, past 85% since December 2025.
Leaderboard import 3 pass
  • Pass Importer We read the board on fretbench.tymo.ai: 21 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