Model comparison
Gemini 2.5 Flash vs MiniMax-M2
Gemini 2.5 Flash is the stronger model overall, scoring 39.3 to 37.4 on the Noometry Index. MiniMax-M2 costs 1.6× less per token, which makes it the better buy when Gemini 2.5 Flash's lead doesn't matter for your workload.
Last verified . 19 shared benchmarks.
Google
MiniMaxSummary
- They share 19 benchmarks with published results for both. Gemini 2.5 Flash scores higher in 6 categories and MiniMax-M2 in 3 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in long context, where Gemini 2.5 Flash leads 47.5 to 40.5.
- The biggest single-benchmark swing is SWE-bench Verified (bash only): 28.7% for Gemini 2.5 Flash and 61% for MiniMax-M2.
- MiniMax-M2 is cheaper at $0.30 / $1.20 per million input/output tokens, against $0.30 / $2.50 for Gemini 2.5 Flash.
- Gemini 2.5 Flash accepts more context: 1.05M tokens versus 205K.
- MiniMax-M2 has downloadable open weights; the other is API-only.
Side by side
| Gemini 2.5 Flash | MiniMax-M2 | |
|---|---|---|
| Provider | MiniMax | |
| Noometry Index | 39.3 | 37.4 |
| Released | 2025-04-17 | 2025-10-27 |
| Weights | Proprietary | Open |
| Context window | 1.05M | 205K |
| Max output | 66K | 131K |
| Input $ / M tokens | $0.30 | $0.30 |
| Output $ / M tokens | $2.50 | $1.20 |
| Results tracked | 54 | 21 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiniMax-M2 leads
Gemini 2.5 Flash: 35.8 (#220), MiniMax-M2: 39.3 (#159)
| Benchmark | Gemini 2.5 Flash | MiniMax-M2 |
|---|---|---|
| SWE-bench Verified (bash only) | 28.7% | 61% |
| LMArena Coding | 1424 | 1370 |
| Aider Polyglot | 55.1% | — |
| LMArena WebDev | — | 1297 |
| WeirdML | 41.9% | — |
| ALE-Bench | 661.88 | — |
Agentic & Tool Use Gemini 2.5 Flash leads
Gemini 2.5 Flash: 30.8 (#74), MiniMax-M2: 25.1 (#109)
| Benchmark | Gemini 2.5 Flash | MiniMax-M2 |
|---|---|---|
| Terminal-Bench | 17.1% | 30% |
| Vending-Bench 2 | 548.84 | 160.6 |
| Berkeley Function Calling Leaderboard | 56.2% | — |
| TheAgentCompany | 41.1% | — |
| BALROG | 33.5% | — |
Reasoning MiniMax-M2 leads
Gemini 2.5 Flash: 18.1 (#286), MiniMax-M2: 19.4 (#258)
| Benchmark | Gemini 2.5 Flash | MiniMax-M2 |
|---|---|---|
| Kagi LLM Benchmark | 56.8% | 57.8% |
| LMArena Hard Prompts | 1422 | 1357 |
| ARC-AGI-2 | 2.5% | — |
| SimpleBench | 41.2% | — |
| NYT Connections (extended) | — | 14.8% |
| ARC-AGI-1 | 33.3% | — |
| CritPt | 1.1% | — |
| EnigmaEval | 2.7% | — |
| DTBench | 76.5% | — |
| LMCA | 27.5% | — |
| Epoch Capabilities Index | 143.03 | — |
| ForecastBench | 60.6 | — |
Math Gemini 2.5 Flash leads
Gemini 2.5 Flash: 39.9 (#98), MiniMax-M2: 37.3 (#160)
| Benchmark | Gemini 2.5 Flash | MiniMax-M2 |
|---|---|---|
| LMArena Math | 1415 | 1352 |
| OTIS Mock AIME 2024-2025 | 73.1% | — |
| Omni-MATH | 38.5% | — |
| FrontierMath (Feb 2025 set) | 4.8% | — |
| FrontierMath Tier 4 (v1) | 4.2% | — |
Knowledge Too close to call
Gemini 2.5 Flash: 36.4 (#168), MiniMax-M2: 37.0 (#163)
| Benchmark | Gemini 2.5 Flash | MiniMax-M2 |
|---|---|---|
| LMArena Expert | 1426 | 1337 |
| Humanity's Last Exam | 12.1% | — |
| MMLU-Pro | 63.9% | — |
| Confabulations | 16.8% | — |
| Vectara Hallucination Rate | 7.8% | — |
| GPQA (HELM) | 39% | — |
Multimodal Not comparable
Gemini 2.5 Flash: 41.8 (#32), MiniMax-M2: —
| Benchmark | Gemini 2.5 Flash | MiniMax-M2 |
|---|---|---|
| LMArena Vision | 1253 | — |
| GeoBench | 76% | — |
| VPCT | 46.2% | — |
| SpatialViz-Bench | 36.9% | — |
Multilingual Gemini 2.5 Flash leads
Gemini 2.5 Flash: 52.3 (#88), MiniMax-M2: 45.3 (#171)
| Benchmark | Gemini 2.5 Flash | MiniMax-M2 |
|---|---|---|
| LMArena Non-English | 1409 | 1313 |
| LMArena Chinese | 1450 | 1366 |
| LMArena French | 1433 | 1335 |
| LMArena German | 1418 | 1355 |
| LMArena Russian | 1415 | 1331 |
| LMArena Spanish | 1421 | 1326 |
| LMArena Japanese | 1405 | — |
| LMArena Korean | 1385 | — |
Instruction Following Gemini 2.5 Flash leads
Gemini 2.5 Flash: 75.7 (#54), MiniMax-M2: 70.2 (#166)
| Benchmark | Gemini 2.5 Flash | MiniMax-M2 |
|---|---|---|
| LMArena Instruction Following | 1405 | 1328 |
| IFEval | 89.8% | — |
Long Context Gemini 2.5 Flash leads
Gemini 2.5 Flash: 47.5 (#17), MiniMax-M2: 40.5 (#153)
| Benchmark | Gemini 2.5 Flash | MiniMax-M2 |
|---|---|---|
| LMArena Longer Query | 1419 | 1331 |
| Fiction.LiveBench | 77.8% | — |
Writing & Preference Too close to call
Gemini 2.5 Flash: 53.8 (#157), MiniMax-M2: 53.0 (#162)
| Benchmark | Gemini 2.5 Flash | MiniMax-M2 |
|---|---|---|
| LMArena Text | 1417 | 1340 |
| LMArena Creative Writing | 1400 | 1286 |
| LMArena Multi-Turn | 1408 | 1361 |
| Short-Story Creative Writing | 76.5% | — |
| EQ-Bench Creative Writing | 1137 | — |
| WildBench | 81.7% | — |
Frequently asked questions
Is Gemini 2.5 Flash better than MiniMax-M2?
Gemini 2.5 Flash is the stronger model overall, scoring 39.3 to 37.4 on the Noometry Index. MiniMax-M2 costs 1.6× less per token, which makes it the better buy when Gemini 2.5 Flash's lead doesn't matter for your workload.
Which is cheaper, Gemini 2.5 Flash or MiniMax-M2?
MiniMax-M2 is cheaper. It lists at $0.30 per million input tokens and $1.20 per million output tokens; Gemini 2.5 Flash lists at $0.30 and $2.50.
Is Gemini 2.5 Flash or MiniMax-M2 better for coding?
MiniMax-M2 scores higher on coding benchmarks: 39.3 versus 35.8 in the Noometry coding category.
Which has the bigger context window?
Gemini 2.5 Flash does, with 1.05M tokens against 205K.
How many benchmarks do Gemini 2.5 Flash and MiniMax-M2 share?
19 benchmarks have published results for both models. Gemini 2.5 Flash has 54 scored results on Noometry and MiniMax-M2 has 21.