MiniMax-Text-01.
MiniMax Jan 2025 Flagship
Its best score on each benchmark, and where that ranks among every model with a score there. We rank each model once, at its best setting.
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| MMLU | 88.5% | #25 of 131 | Lab model card | |
| Arena-Hard-Auto | 89.1% | #11 of 39 | Lab model card | |
| DROP | 87.8% | #13 of 41 | Lab model card | |
| IFEval | 89.1% | #43 of 135 | Lab model card | |
| RULER | 91% | #20 of 42 | Lab model card | |
| SuperGPQA | 45.1% | #29 of 59 | Official leaderboard | |
| LongBench v2 | 56.5% | #19 of 35 | Lab model card | |
| SimpleQA | 23.7% | #35 of 60 | Lab model card | |
| MMLU-Pro | 75.7% | #107 of 167 | Lab model card | |
| MTOB | 51.7 | #2 of 3 | Lab model card | |
| Chinese SimpleQA | 67.4% | #10 of 13 | Lab model card | |
| LLM Confabulation Leaderboard | 23.9% | #47 of 58 | Official leaderboard | |
| Creative Writing (MiniMax in-house) | 81.3% | #1 of 1 | Lab model card | |
| General Assistant (MiniMax in-house) | 73.9% | #1 of 1 | Lab model card | |
| Hard Capability (MiniMax in-house) | 64.8% | #1 of 1 | Lab model card | |
| Instruction Following (MiniMax in-house) | 46.3% | #1 of 1 | Lab model card | |
| Knowledge Q&A (MiniMax in-house) | 78.6% | #1 of 1 | Lab model card | |
| Long Context (MiniMax in-house) | 93.8% | #1 of 1 | Lab model card |
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| GSM8K | 94.8% | #15 of 92 | Lab model card | |
| MATH | 77.4% | #32 of 99 | Lab model card | |
| Misguided Attention | 36.5% | #28 of 45 | Official leaderboard | |
| GPQA Diamond | 54.4% | #234 of 302 | Lab model card |
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| HumanEval | 86.9% | #33 of 101 | Lab model card | |
| MBPP | 71.7% | #44 of 71 | Lab model card | |
| EvalPlus | 71.7% | #6 of 6 | Lab model card | |
| Coding (MiniMax in-house) | 90.2% | #1 of 1 | Lab model card |
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| Elimination Game | 3 | #39 of 56 | Official leaderboard |
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| Safety (MiniMax in-house) | 90.9% | #1 of 1 | Lab model card |
The Self-Reported Index fits one score to the 14 capability results MiniMax reported for this model, on the scale of the Epoch Capabilities Index. Labs choose which benchmarks to show and how to run them, so read it as the lab's claim, not an independent measurement. The 90% interval runs from 127.4 to 132.6. How we compute it.
Where the benchmark's own leaderboard, or Epoch AI's run, also has this model. Gaps mostly come from different harnesses, effort levels and task subsets. Every pair.
The benchmarks the lab chose to headline, with the scores it gave.
Every result in the longer documents the lab published with it. 11 of them aren't in the launch post.