MuSeToM - Task 1 - F1: leaderboard
MuSeToM - Task 1 - F1 — MuSeToM v1 Table1 direct prompting on human-validated textual belief revision; clean tasks1binary/2multiplechoice and noisy tasks3binary/4multiplechoice remain separate. Accuracy and Macro-F1 are distinct percentage metrics. AppendixB.1 binds the Llama/Mistral/Mixtral instruction checkpoints; Tables23and28–31bind the sole Phi row to Phi-3-Medium-4K-Instruct in the same18-model cohort. temperature0,top_p1,1024output tokens for the listed first group and10240for later reasoning models; Phi output budget is unreported because B.1omits it. Effort/API dated snapshots are unreported. Eighteen model rows; Human reference is a separate reference, not Median Human/Expert and not an AI model. Main table shorthand is resolved from this paper only; no global Base/Instruct or generation alias. Metric: Macro-F1 (%).
Metric: Macro-F1 (%). Source: arxiv.org. Saturation forecast: Around February 2027. 18 models tracked. Updated 15 Nov 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | MiniMax-M2.5 | 86.05 | #584 |
| 2 | Qwen 3.5 397B A17B | 85.34 | #251 |
| 3 | QwQ-32B | 82.61 | #915 |
| 4 | DeepSeek V3.1 | 82.57 | #502 |
| 5 | GPT-OSS-120B | 82.53 | #703 |
| 6 | MiniMax-M2.1 | 78.54 | #574 |
| 7 | DeepSeek R1 | 77.54 | #478 |
| 8 | Llama 3.1 405B Instruct | 77.25 | #1122 |
| 9 | DeepSeek V3.2 | 75.57 | #412 |
| 10 | GPT-4o | 70.09 | #744 |
| 11 | Qwen 3 235B A22B | 67.75 | #628 |
| 12 | Llama 4 Maverick Instruct | 67.51 | #1163 |
| 13 | Kimi K2 (Thinking) | 65.5 | |
| 14 | Mixtral 8x22B Instruct | 63.35 | #2097 |
| 15 | Phi-3-medium-4k-instruct | 55.72 | #2696 |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.
Interactive version: theaggregate.ai/benchmark?slug=musetom-task-1-f1 · How It Works · Data refreshed daily, snapshot 2026-11-16.