MiniMax-M3
MiniMax multimodal model for long-context coding, perception, and agent planning
Shogo Agent Index
Estimated#61 of 9236.7range 26.5–46.8 · 20% of weight measured
Agentic coding
37
estimated
Long-horizon autonomy
49
30% measured
Knowledge-work agents
31
32% measured
Computer use
24
60% measured
Security & context learning
37
estimated
Agentic benchmarks
| Benchmark | Score | Normalised | Index weight | Harness / source |
|---|---|---|---|---|
| SWE-bench Verified | est. | 8% | predicted 69 | |
| Terminal-Bench 2.0 | est. | 8% | predicted 44 | |
| DeepSWE | est. | 6% | predicted 30 | |
| FrontierSWE | est. | 5% | predicted 6 | |
| CursorBench | est. | 4% | predicted 29 | |
| GSO-Bench | est. | 4% | predicted 12 | |
| METR Time Horizons | est. | 10% | predicted 67 | |
| Vending-Bench 2 | $2,158 | 6% | source | |
| PostTrainBench | est. | 4% | predicted 19 | |
| APEX-Agents | 37.7% | 8% | source | |
| GDPval | est. | 7% | predicted 35 | |
| Remote Labor Index | est. | 5% | predicted 2 | |
| DeepResearch Bench | est. | 5% | predicted 46 | |
| OSWorld 2.0 | 4.6% | 6% | source | |
| OSWorld | est. | 4% | predicted 54 | |
| Cybench | est. | 5% | predicted 55 | |
| CL-bench | est. | 5% | predicted 18 |
Other benchmarks
| Benchmark | Category | Score | Source |
|---|---|---|---|
| Chess Puzzles | Reasoning | 17.0% | source |
| CritPt | Reasoning | 3.7% | source |
| DTBench | Knowledge | 78.9% | source |
| FrontierCode | Coding | 14.7% | mini-swe-agent |
| GPQA Diamond | Reasoning | 90.9% | source |
| LMCA | Knowledge | 33.7% | source |
| OTIS Mock AIME | Math | 71.1% | source |
| ProofBench | Math | 18.0% | source |
| SciCode | Coding | 47.1% | source |
| SimpleBench | Reasoning | 45.8% | source |
| WebDev Arena | Coding | 1487 | source |
API hosts
Live prices and uptime for every host serving MiniMax-M3 via OpenRouter.
| Host | Input | Output | Cache read | Agent $/M | Uptime 24h | Quant |
|---|---|---|---|---|---|---|
| DeepInfra | $0.22 | $0.88 | $0.045 | $0.11 | 100.0% | fp8 |
| CoreWeave | $0.23 | $0.96 | $0.050 | $0.12 | 96.9% | fp4 |
| GMICloud | $0.24 | $0.96 | $0.048 | $0.12 | 100.0% | fp8 |
| DeepInfra | $0.28 | $1.10 | $0.056 | $0.14 | 100.0% | fp8 |
| Minimax | $0.30 | $1.20 | $0.060 | $0.15 | 100.0% | — |
| Parasail | $0.30 | $1.20 | $0.060 | $0.15 | 99.9% | fp8 |
| Venice | $0.30 | $1.20 | $0.060 | $0.15 | 99.3% | fp8 |
| Parasail | $0.45 | $1.80 | $0.090 | $0.22 | 99.6% | fp8 |
| Featherless | $0.55 | $2.20 | $0.060 | $0.23 | 10.3% | fp8 |