MiniMax-M2.5
| Released | 2026-02-12 |
|---|---|
| Price per 1M | $0.30 in · $1.20 out |
| Overall score | 49.3 · rank 118 |
| Context window | 204,800 tokens |
| Provider | MiniMax |
| Weights | Open weights |
Scores
| Dimension | Score | Rank | Benchmarks |
|---|---|---|---|
| Overall: Balanced | 49.3 | 118 | 16 |
| Overall: Coding | 50.4 | 108 | 11 |
| Overall: Reasoning | 48.7 | 126 | 7 |
| Overall: Agentic work | 49.4 | 117 | 9 |
| Overall: Frontend | 47.0 | 118 | 4 |
| Coding | 53.3 | 93 | 2 |
| Agents | 47.7 | 122 | 2 |
| Reasoning | 49.7 | 118 | 5 |
| Math | 50.4 | 106 | 1 |
| Knowledge | 43.4 | 122 | 1 |
| Frontend | 43.8 | 99 | 2 |
| General | 49.6 | 113 | 3 |
| Value vs price | +3.5 | 93 |
Evidence
Coding 53.3 ±3.3
| Benchmark | Result | Source | Date |
|---|---|---|---|
| SWE-bench Verified (Vals run) | 74.2% | Vals AI | 2026-09-01 |
| LiveCodeBench (Vals run) | 79.2% | Vals AI | 2026-09-01 |
Agents 47.7 ±2.4
| Benchmark | Result | Source | Date |
|---|---|---|---|
| Terminal-Bench 2.0 | 42.7% | Epoch AI | 2026-02-12 |
| Vending-Bench 2 | $-23 | Epoch AI | 2026-11-11 |
Reasoning 49.7 ±2.3
| Benchmark | Result | Source | Date |
|---|---|---|---|
| Extended NYT Connections | 16.8% | Lech Mazur | 2026-11-10 |
| ARC-AGI-2 | 4.9% | Epoch AI | 2026-11-11 |
| ARC-AGI-2 (ARC Prize verified) | 4.9% | ARC Prize | 2026-11-11 |
| GPQA Diamond (Vals run) | 82.1% | Vals AI | 2026-09-01 |
| ARC-AGI-1 (ARC Prize verified) | 63.7% | ARC Prize | 2026-11-11 |
| ARC-AGI-1 | 63.7% | Epoch AI | 2026-11-11 |
| Kagi Reasoning Benchmark | 55.2% | Kagi | 2026-11-11 |
Math 50.4 ±3.1
| Benchmark | Result | Source | Date |
|---|---|---|---|
| ProofBench | 4.0% | Epoch AI | 2026-11-11 |
Knowledge 43.4 ±4.7
| Benchmark | Result | Source | Date |
|---|---|---|---|
| MMLU-Pro (Vals run) | 80.1% | Vals AI | 2026-09-01 |
Frontend 43.8 ±0.7
| Benchmark | Result | Source | Date |
|---|---|---|---|
| Vibe Code Bench v1.1 | 14.9% | Vals AI | 2026-11-09 |
| LMArena WebDev | 1,386 | LMArena | 2026-11-10 |
General 49.6 ±3.5
| Benchmark | Result | Source | Date |
|---|---|---|---|
| LMArena Text | 1,391 | LMArena | 2026-11-09 |
| EQ-Bench Creative Writing v3 | 1,362 | EQ-Bench | 2026-11-11 |
| EQ-Bench Longform Creative Writing | 65.3% | EQ-Bench | 2026-11-11 |
Results not used in the score
| Benchmark | Result | Source | Why not used |
|---|---|---|---|
| Terminal-Bench 2.0 | 42.3% | Epoch AI | A stronger configuration result was used |
Names matched to this model
minimax-m2-5