Model comparison
Gemini 2.0 Flash (Feb 2025) vs MiniMax-M2.5
MiniMax-M2.5 is the stronger model overall, scoring 38.3 to 35.1 on the Noometry Index.
Last verified . 22 shared benchmarks.
Google
MiniMaxSummary
- They share 22 benchmarks with published results for both. Gemini 2.0 Flash (Feb 2025) scores higher in 4 categories and MiniMax-M2.5 in 5 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in coding, where MiniMax-M2.5 leads 48.1 to 28.4.
- The biggest single-benchmark swing is SWE-bench Verified (bash only): 13.5% for Gemini 2.0 Flash (Feb 2025) and 75.8% for MiniMax-M2.5.
- MiniMax-M2.5 has downloadable open weights; the other is API-only.
Side by side
| Gemini 2.0 Flash (Feb 2025) | MiniMax-M2.5 | |
|---|---|---|
| Provider | MiniMax | |
| Noometry Index | 35.1 | 38.3 |
| Released | 2024-12-06 | 2026-02-12 |
| Weights | Proprietary | Open |
| Context window | — | 205K |
| Max output | — | 131K |
| Input $ / M tokens | — | $0.30 |
| Output $ / M tokens | — | $1.20 |
| Results tracked | 54 | 33 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiniMax-M2.5 leads
Gemini 2.0 Flash (Feb 2025): 28.4 (#315), MiniMax-M2.5: 48.1 (#58)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | MiniMax-M2.5 |
|---|---|---|
| SWE-bench Verified (bash only) | 13.5% | 75.8% |
| LMArena Coding | 1350 | 1381 |
| Aider Polyglot | 38.2% | — |
| LMArena WebDev | — | 1387 |
| SWE-bench Multilingual | — | 68.3% |
| WeirdML | 25.8% | — |
| BigCodeBench Instruct | 45.9% | — |
| LiveBench Coding | 63.4% | — |
| BigCodeBench Complete | 59.9% | — |
| CadEval | 30% | — |
| ALE-Bench | — | 618.17 |
Agentic & Tool Use MiniMax-M2.5 leads
Gemini 2.0 Flash (Feb 2025): 28.1 (#92), MiniMax-M2.5: 30.4 (#77)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | MiniMax-M2.5 |
|---|---|---|
| Terminal-Bench | — | 42.7% |
| TheAgentCompany | 11.4% | — |
| Vending-Bench 2 | — | -23.16 |
Reasoning MiniMax-M2.5 leads
Gemini 2.0 Flash (Feb 2025): 15.2 (#318), MiniMax-M2.5: 17.5 (#292)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | MiniMax-M2.5 |
|---|---|---|
| ARC-AGI-2 | 1.3% | 4.9% |
| Kagi LLM Benchmark | 37.8% | 55.2% |
| LMArena Hard Prompts | 1346 | 1372 |
| Epoch Capabilities Index | 135.36 | 146.68 |
| SimpleBench | 31.1% | — |
| NYT Connections (extended) | — | 16.8% |
| ARC-AGI-1 | — | 63.7% |
| EnigmaEval | 1.1% | — |
| LiveBench Reasoning | 78.2% | — |
| DTBench | 63.2% | — |
| LiveBench Data Analysis | 69.4% | — |
| LiveBench | 66.9% | — |
Math Gemini 2.0 Flash (Feb 2025) leads
Gemini 2.0 Flash (Feb 2025): 37.9 (#146), MiniMax-M2.5: 26.9 (#253)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | MiniMax-M2.5 |
|---|---|---|
| LMArena Math | 1352 | 1378 |
| OTIS Mock AIME 2024-2025 | 57.8% | — |
| ProofBench | — | 4% |
| Omni-MATH | 45.9% | — |
| LiveBench Math | 75.8% | — |
| MATH Level 5 | 82.2% | — |
| FrontierMath (Feb 2025 set) | 1.7% | — |
Knowledge MiniMax-M2.5 leads
Gemini 2.0 Flash (Feb 2025): 32.0 (#213), MiniMax-M2.5: 39.2 (#135)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | MiniMax-M2.5 |
|---|---|---|
| LMArena Expert | 1339 | 1379 |
| GPQA Diamond | 64.1% | — |
| Humanity's Last Exam | 6.6% | — |
| MMLU-Pro | 73.7% | — |
| Confabulations | 12.4% | — |
| Vectara Hallucination Rate | — | 9.1% |
| GPQA (HELM) | 55.6% | — |
| MMLU | 79.7% | — |
Multimodal Not comparable
Gemini 2.0 Flash (Feb 2025): 36.5 (#79), MiniMax-M2.5: —
| Benchmark | Gemini 2.0 Flash (Feb 2025) | MiniMax-M2.5 |
|---|---|---|
| LMArena Vision | 1158 | — |
| GeoBench | 77% | — |
Multilingual Too close to call
Gemini 2.0 Flash (Feb 2025): 47.4 (#149), MiniMax-M2.5: 47.1 (#152)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | MiniMax-M2.5 |
|---|---|---|
| LMArena Non-English | 1342 | 1338 |
| LMArena Chinese | 1373 | 1393 |
| LMArena French | 1391 | 1362 |
| LMArena German | 1353 | 1362 |
| LMArena Japanese | 1294 | 1171 |
| LMArena Korean | 1313 | 1232 |
| LMArena Russian | 1351 | 1358 |
| LMArena Spanish | 1363 | 1354 |
Instruction Following Gemini 2.0 Flash (Feb 2025) leads
Gemini 2.0 Flash (Feb 2025): 74.4 (#97), MiniMax-M2.5: 71.5 (#148)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | MiniMax-M2.5 |
|---|---|---|
| LMArena Instruction Following | 1336 | 1353 |
| LiveBench Instruction Following | 85.8% | — |
| IFEval | 84.1% | — |
Long Context Too close to call
Gemini 2.0 Flash (Feb 2025): 38.1 (#203), MiniMax-M2.5: 37.5 (#216)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | MiniMax-M2.5 |
|---|---|---|
| LMArena Longer Query | 1344 | 1366 |
| Fiction.LiveBench | 61.1% | — |
| CL-bench | — | 11.4% |
| CL-bench Life | — | 6.3% |
Writing & Preference MiniMax-M2.5 leads
Gemini 2.0 Flash (Feb 2025): 49.5 (#190), MiniMax-M2.5: 53.9 (#153)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | MiniMax-M2.5 |
|---|---|---|
| LMArena Text | 1354 | 1359 |
| LMArena Creative Writing | 1340 | 1331 |
| EQ-Bench Creative Writing | 1128 | 1361 |
| LMArena Multi-Turn | 1350 | 1364 |
| Short-Story Creative Writing | 73.8% | — |
| WildBench | 80% | — |
| LiveBench Language | 51.3% | — |
Frequently asked questions
Is Gemini 2.0 Flash (Feb 2025) better than MiniMax-M2.5?
MiniMax-M2.5 is the stronger model overall, scoring 38.3 to 35.1 on the Noometry Index.
Is Gemini 2.0 Flash (Feb 2025) or MiniMax-M2.5 better for coding?
MiniMax-M2.5 scores higher on coding benchmarks: 48.1 versus 28.4 in the Noometry coding category.
How many benchmarks do Gemini 2.0 Flash (Feb 2025) and MiniMax-M2.5 share?
22 benchmarks have published results for both models. Gemini 2.0 Flash (Feb 2025) has 54 scored results on Noometry and MiniMax-M2.5 has 33.