MiniMax M3 minimax-m3
minimax · minimax reasoning flagship agentic
#12 overall
- params
- 427B
- arch
- moe
- context
- 1024k
- license
- other open weights
- released
- Jun 2026
- reasoning
- yes
- downloads/30d
- 201.1k
# architecture
- layers
- 60
- d_model
- 6144
- heads
- 64q / 4kv
- head dim
- 128
- experts
- top-4 of 128 + 1 shared
- vocab
- 200064
- family
- minimax_m3_vl
signal path of one layer, generated from the registry's structured fields — dimension lines quote the model's real numbers; an MoE trace forks at the router, a dense trace runs straight through. Geometry fields come from the repo's config.json.
# why ranked
Overall: #12 — score 86.4 ● high — all signals present
| signal | weight | input (0–100) |
|---|---|---|
| aa_intelligence | 0.70 | 85.4 |
| bench_composite | 0.30 | 88.9 |
benchmark panel evidence:
| complete panel | score (0–100) |
|---|---|
| aa-coding-v1 | 86.6 |
| browsecomp-v1 | 100.0 |
| livebench-v1 | 80.0 |
Coding: provisional — score 76.5 ● low — a single signal; treat with caution
provisional: too few independent signals for a numbered position — the score is shown, but this model sorts after every ranked model.
| signal | weight | input (0–100) |
|---|---|---|
| aa_coding | 0.30 | 76.5 |
| aider_polyglot | 0.30 | — |
| swe_bench_verified | 0.40 | — |
missing signals are dropped and the remaining weights renormalized — never imputed.
# trend
methodology changed during this history window; score movement across that boundary is not model movement. See methodology v6.
# benchmarks
| benchmark | score | source | date |
|---|---|---|---|
| AA Coding Index | 58.6 | Artificial Analysis | — |
| AA Intelligence Index | 29.2 | Artificial Analysis | — |
| LiveBench Agentic Coding | 40.7 | LiveBench | Jun 2026 |
| LiveBench Coding | 68.2 | LiveBench | Jun 2026 |
| LiveBench Data Analysis | 76.2 | LiveBench | Jun 2026 |
| LiveBench IF | 57.5 | LiveBench | Jun 2026 |
| LiveBench Language | 76.8 | LiveBench | Jun 2026 |
| LiveBench Mathematics | 76.9 | LiveBench | Jun 2026 |
| LiveBench Reasoning | 74.5 | LiveBench | Jun 2026 |
| Apex-agents | 0.3 / 1 | LLM Stats | — |
| Bankertoolbench | 0.8 / 1 | LLM Stats | — |
| Browsecomp | 0.8 / 1 | LLM Stats | — |
| Cl-bench | 0.2 / 1 | LLM Stats | — |
| Claw-eval | 0.7 / 1 | LLM Stats | — |
| Imo-2025 | 35.0 / 42 | LLM Stats | — |
| Usamo-2026 | 36.0 / 42 | LLM Stats | — |
| Yc-bench | 2100000.0 / 10000000 | LLM Stats | — |
# where to run
| provider | quant | ctx | $/M in | $/M out | $/M cache | price src | tps | uptime | ✓ |
|---|---|---|---|---|---|---|---|---|---|
| Featherless | — | — | — | — | via hfrouter | — | — | ||
| Nebius | — | — | — | — | nebius | — | — | ✓ | |
| SiliconFlow | — | — | — | — | siliconflow | — | — | ✓ | |
| Vultr | 512k | $0.20 | $0.90 | — | via modelsdev | — | — | ||
| CoreWeave | fp4 | 256k | $0.23 | $0.96 | $0.05 | via openrouter | — | 97.9% | |
| Wandb | 262k | $0.23 | $0.96 | — | via litellm | — | — | ||
| GMICloud | fp8 | 1024k | $0.24 | $0.96 | $0.05 | via openrouter | — | 99.8% | |
| DeepInfra | fp8 | 512k | $0.28 | $1.10 | — | deepinfra | — | 100.0% | ✓ |
| DeepInfra | fp8 | 512k | $0.28 | $1.10 | — | deepinfra | — | 99.7% | ✓ |
| Aihubmix | 1000k | $0.29 | $1.15 | — | via litellm | — | — | ||
| AtlasCloud | fp8 | 524k | $0.30 | $1.20 | — | atlascloud | — | 99.9% | ✓ |
| Fireworks | 500k | $0.30 | $1.20 | $0.06 | via requesty | — | — | ||
| Minimax | fp8 | 512k | $0.30 | $1.20 | $0.06 | via openrouter | — | 100.0% | |
| Novita | fp8 | 1000k | $0.30 | $1.20 | — | novita | — | 100.0% | ✓ |
| Opencode Go | 1000k | $0.30 | $1.20 | — | via litellm | — | — | ||
| Parasail | fp8 | 1024k | $0.30 | $1.20 | $0.06 | via openrouter | — | 99.5% | |
| StreamLake | fp8 | 1000k | $0.30 | $1.20 | $0.06 | via openrouter | — | 99.7% | |
| Tencent | 1000k | $0.30 | $1.20 | — | via litellm | — | — | ||
| Together | unknown | 512k | $0.30 | $1.20 | $0.06 | via openrouter | — | 100.0% | |
| Venice | fp8 | 512k | $0.30 | $1.20 | — | venice | — | 99.9% | ✓ |
| ModelRun | fp8 | 1024k | $0.30 | $1.30 | $0.05 | via openrouter | — | 99.9% | |
| Inferenceapis | 512k | $0.39 | $1.56 | — | via litellm | — | — | ||
| Mara | unknown | 1024k | $0.60 | $2.40 | — | via openrouter | — | 60.0% | |
| SambaNova | 1024k | $0.60 | $2.40 | $0.06 | via modelsdev | — | — |
sorted by blended price ((3·input + output) / 4 per 1M) · ✓ = the provider's own catalog confirms the offer · "via …" prices are what the aggregator routing the offer charges, not the provider's own list price
source aliases
- aa
minimax-m3- arena
MiniMax-M3- openrouter
minimax/minimax-m3