MiniMax-M2.7
| Released | 2026-03-18 |
|---|---|
| Price per 1M | $0.30 in · $1.20 out |
| Overall score | 50.1 · rank 112 |
| Context window | 204,800 tokens |
| Provider | MiniMax |
| Weights | Open weights |
Scores
| Dimension | Score | Rank | Benchmarks |
|---|---|---|---|
| Overall: Balanced | 50.1 | 112 | 17 |
| Overall: Coding | 51.3 | 102 | 11 |
| Overall: Reasoning | 48.0 | 132 | 6 |
| Overall: Agentic work | 51.6 | 104 | 9 |
| Overall: Frontend | 46.4 | 122 | 6 |
| Coding | 54.2 | 84 | 4 |
| Agents | 51.3 | 98 | 2 |
| Reasoning | 48.6 | 126 | 3 |
| Math | 49.7 | 116 | 1 |
| Knowledge | 43.7 | 120 | 2 |
| Frontend | 42.5 | 104 | 2 |
| General | 50.4 | 103 | 3 |
| Value vs price | +4.3 | 84 |
Evidence
Coding 54.2 ±2.5
| Benchmark | Result | Source | Date |
|---|---|---|---|
| SWE-bench Verified (Vals run) | 73.8% | Vals AI | 2026-09-01 |
| SciCode | 50.1% | Epoch AI | 2026-11-11 |
| LiveCodeBench (Vals run) | 79.9% | Vals AI | 2026-09-01 |
| ProgramBench | 0.0% | Vals AI | 2026-11-09 |
Agents 51.3 ±2.4
| Benchmark | Result | Source | Date |
|---|---|---|---|
| Terminal-Bench 2.0 | 45.1% | Epoch AI | 2026-03-18 |
| Tax Agent Bench | 6.9% | Vals AI | 2026-11-09 |
| Terminal-Bench 2.1 (Vals run) | 48.7% | Vals AI | 2026-10-01 |
Reasoning 48.6 ±6.7
| Benchmark | Result | Source | Date |
|---|---|---|---|
| Extended NYT Connections | 24.7% | Lech Mazur | 2026-11-10 |
| GPQA Diamond (Vals run) | 86.6% | Vals AI | 2026-09-01 |
| CritPt | 0.6% | Epoch AI | 2026-11-11 |
Math 49.7 ±3.1
| Benchmark | Result | Source | Date |
|---|---|---|---|
| ProofBench | 3.0% | Epoch AI | 2026-11-11 |
Knowledge 43.7 ±3.9
| Benchmark | Result | Source | Date |
|---|---|---|---|
| MMLU-Pro (Vals run) | 80.4% | Vals AI | 2026-09-01 |
| Legal Research Bench | 10.6% | Vals AI | 2026-11-09 |
Frontend 42.5 ±0.7
| Benchmark | Result | Source | Date |
|---|---|---|---|
| Vibe Code Bench v1.1 | 11.9% | Vals AI | 2026-11-09 |
| LMArena WebDev | 1,398 | LMArena | 2026-11-09 |
General 50.4 ±3.1
| Benchmark | Result | Source | Date |
|---|---|---|---|
| LMArena Text | 1,415 | LMArena | 2026-11-09 |
| LLM Debate Benchmark | 1,426 | Lech Mazur | 2026-10-26 |
| Creative Story-Writing (Lech Mazur) | 6.0% | Lech Mazur | 2026-10-23 |
Results not used in the score
| Benchmark | Result | Source | Why not used |
|---|---|---|---|
| Terminal-Bench 2.0 | 42.9% | Epoch AI | A stronger configuration result was used |
Names matched to this model
minimax-m2-7