Model comparison
Llama 4 Scout vs MiniMax-M2
MiniMax-M2 is the stronger model overall, scoring 37.4 to 27.7 on the Noometry Index. Llama 4 Scout costs 3.5× less per token, which makes it the better buy when MiniMax-M2's lead doesn't matter for your workload.
Last verified . 17 shared benchmarks.
Meta
MiniMaxSummary
- They share 17 benchmarks with published results for both. Llama 4 Scout scores higher in 0 categories and MiniMax-M2 in 9 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in coding, where MiniMax-M2 leads 39.3 to 20.2.
- The biggest single-benchmark swing is SWE-bench Verified (bash only): 9.1% for Llama 4 Scout and 61% for MiniMax-M2.
- Llama 4 Scout is cheaper at $0.10 / $0.30 per million input/output tokens, against $0.30 / $1.20 for MiniMax-M2.
- MiniMax-M2 accepts more context: 205K tokens versus 128K.
Side by side
| Llama 4 Scout | MiniMax-M2 | |
|---|---|---|
| Provider | Meta | MiniMax |
| Noometry Index | 27.7 | 37.4 |
| Released | 2025-04-05 | 2025-10-27 |
| Weights | Open | Open |
| Context window | 128K | 205K |
| Max output | 4K | 131K |
| Input $ / M tokens | $0.10 | $0.30 |
| Output $ / M tokens | $0.30 | $1.20 |
| Results tracked | 43 | 21 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiniMax-M2 leads
Llama 4 Scout: 20.2 (#339), MiniMax-M2: 39.3 (#159)
| Benchmark | Llama 4 Scout | MiniMax-M2 |
|---|---|---|
| SWE-bench Verified (bash only) | 9.1% | 61% |
| LMArena Coding | 1286 | 1370 |
| LMArena WebDev | — | 1297 |
| SciCode | 17% | — |
| BigCodeBench Complete | 43.1% | — |
Agentic & Tool Use Too close to call
Llama 4 Scout: 24.6 (#119), MiniMax-M2: 25.1 (#109)
| Benchmark | Llama 4 Scout | MiniMax-M2 |
|---|---|---|
| Terminal-Bench | — | 30% |
| Berkeley Function Calling Leaderboard | 28.1% | — |
| Vending-Bench 2 | — | 160.6 |
Reasoning MiniMax-M2 leads
Llama 4 Scout: 9.1 (#345), MiniMax-M2: 19.4 (#258)
| Benchmark | Llama 4 Scout | MiniMax-M2 |
|---|---|---|
| Kagi LLM Benchmark | 36.9% | 57.8% |
| LMArena Hard Prompts | 1266 | 1357 |
| ARC-AGI-2 | 0% | — |
| NYT Connections (extended) | — | 14.8% |
| ARC-AGI-1 | 0.5% | — |
| CritPt | 0% | — |
| DTBench | 57.9% | — |
| LMCA | 12% | — |
| Epoch Capabilities Index | 129.64 | — |
| ForecastBench | 57.5 | — |
Math MiniMax-M2 leads
Llama 4 Scout: 19.6 (#286), MiniMax-M2: 37.3 (#160)
| Benchmark | Llama 4 Scout | MiniMax-M2 |
|---|---|---|
| LMArena Math | 1287 | 1352 |
| OTIS Mock AIME 2024-2025 | 7.8% | — |
| Omni-MATH | 37.3% | — |
| MATH Level 5 | 62.3% | — |
| FrontierMath (Feb 2025 set) | 0% | — |
Knowledge MiniMax-M2 leads
Llama 4 Scout: 31.9 (#217), MiniMax-M2: 37.0 (#163)
| Benchmark | Llama 4 Scout | MiniMax-M2 |
|---|---|---|
| LMArena Expert | 1235 | 1337 |
| GPQA Diamond | 51.8% | — |
| MMLU-Pro | 74.2% | — |
| Vectara Hallucination Rate | 7.7% | — |
| GPQA (HELM) | 50.7% | — |
Multimodal Not comparable
Llama 4 Scout: 32.2 (#102), MiniMax-M2: —
| Benchmark | Llama 4 Scout | MiniMax-M2 |
|---|---|---|
| LMArena Vision | 1118 | — |
| SpatialViz-Bench | 34.2% | — |
Multilingual MiniMax-M2 leads
Llama 4 Scout: 41.0 (#212), MiniMax-M2: 45.3 (#171)
| Benchmark | Llama 4 Scout | MiniMax-M2 |
|---|---|---|
| LMArena Non-English | 1252 | 1313 |
| LMArena Chinese | 1255 | 1366 |
| LMArena French | 1282 | 1335 |
| LMArena German | 1272 | 1355 |
| LMArena Russian | 1263 | 1331 |
| LMArena Spanish | 1278 | 1326 |
| LMArena Japanese | 1206 | — |
| LMArena Korean | 1207 | — |
Instruction Following MiniMax-M2 leads
Llama 4 Scout: 65.8 (#217), MiniMax-M2: 70.2 (#166)
| Benchmark | Llama 4 Scout | MiniMax-M2 |
|---|---|---|
| LMArena Instruction Following | 1248 | 1328 |
| IFEval | 81.8% | — |
Long Context MiniMax-M2 leads
Llama 4 Scout: 27.5 (#294), MiniMax-M2: 40.5 (#153)
| Benchmark | Llama 4 Scout | MiniMax-M2 |
|---|---|---|
| LMArena Longer Query | 1265 | 1331 |
| Fiction.LiveBench | 36% | — |
Writing & Preference MiniMax-M2 leads
Llama 4 Scout: 37.0 (#261), MiniMax-M2: 53.0 (#162)
| Benchmark | Llama 4 Scout | MiniMax-M2 |
|---|---|---|
| LMArena Text | 1279 | 1340 |
| LMArena Creative Writing | 1249 | 1286 |
| LMArena Multi-Turn | 1280 | 1361 |
| EQ-Bench Creative Writing | 783 | — |
| WildBench | 78% | — |
Frequently asked questions
Is Llama 4 Scout better than MiniMax-M2?
MiniMax-M2 is the stronger model overall, scoring 37.4 to 27.7 on the Noometry Index. Llama 4 Scout costs 3.5× less per token, which makes it the better buy when MiniMax-M2's lead doesn't matter for your workload.
Which is cheaper, Llama 4 Scout or MiniMax-M2?
Llama 4 Scout is cheaper. It lists at $0.10 per million input tokens and $0.30 per million output tokens; MiniMax-M2 lists at $0.30 and $1.20.
Is Llama 4 Scout or MiniMax-M2 better for coding?
MiniMax-M2 scores higher on coding benchmarks: 39.3 versus 20.2 in the Noometry coding category.
Which has the bigger context window?
MiniMax-M2 does, with 205K tokens against 128K.
How many benchmarks do Llama 4 Scout and MiniMax-M2 share?
17 benchmarks have published results for both models. Llama 4 Scout has 43 scored results on Noometry and MiniMax-M2 has 21.