Model comparison
Gemini 1.5 Pro (May 2024) vs MiniMax-M2.7
MiniMax-M2.7 is the stronger model overall, scoring 37.4 to 31.9 on the Noometry Index.
Last verified . 19 shared benchmarks.
Google
MiniMaxSummary
- They share 19 benchmarks with published results for both. Gemini 1.5 Pro (May 2024) scores higher in 0 categories and MiniMax-M2.7 in 9 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where MiniMax-M2.7 leads 37.1 to 29.3.
- The biggest single-benchmark swing is WeirdML: 22.2% for Gemini 1.5 Pro (May 2024) and 37% for MiniMax-M2.7.
- MiniMax-M2.7 has downloadable open weights; the other is API-only.
Side by side
| Gemini 1.5 Pro (May 2024) | MiniMax-M2.7 | |
|---|---|---|
| Provider | MiniMax | |
| Noometry Index | 31.9 | 37.4 |
| Released | 2024-02-15 | 2026-03-18 |
| Weights | Proprietary | Open |
| Context window | — | 205K |
| Max output | — | 131K |
| Input $ / M tokens | — | $0.30 |
| Output $ / M tokens | — | $1.20 |
| Results tracked | 45 | 30 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiniMax-M2.7 leads
Gemini 1.5 Pro (May 2024): 33.8 (#239), MiniMax-M2.7: 41.4 (#115)
| Benchmark | Gemini 1.5 Pro (May 2024) | MiniMax-M2.7 |
|---|---|---|
| WeirdML | 22.2% | 37% |
| LMArena Coding | 1294 | 1454 |
| LMArena WebDev | — | 1397 |
| SciCode | — | 47% |
| BigCodeBench Instruct | 43.8% | — |
| BigCodeBench Complete | 57.5% | — |
| CadEval | 34% | — |
| ALE-Bench | — | 599.25 |
| HumanEval+ | 79.3% | — |
| MBPP+ | 74.6% | — |
Agentic & Tool Use MiniMax-M2.7 leads
Gemini 1.5 Pro (May 2024): 17.8 (#137), MiniMax-M2.7: 24.9 (#103)
| Benchmark | Gemini 1.5 Pro (May 2024) | MiniMax-M2.7 |
|---|---|---|
| Terminal-Bench | — | 45.1% |
| TheAgentCompany | 3.4% | — |
| Cybench | 7.5% | — |
| BALROG | 21% | — |
| ExploitBench | — | 13.3% |
| GBAEval | — | 0% |
Reasoning MiniMax-M2.7 leads
Gemini 1.5 Pro (May 2024): 12.3 (#332), MiniMax-M2.7: 19.0 (#248)
| Benchmark | Gemini 1.5 Pro (May 2024) | MiniMax-M2.7 |
|---|---|---|
| LMArena Hard Prompts | 1296 | 1422 |
| Epoch Capabilities Index | 131.73 | 145.84 |
| ARC-AGI-2 | 0.8% | — |
| SimpleBench | 27.1% | — |
| NYT Connections (extended) | — | 24.7% |
| CritPt | — | 0.6% |
| Thematic Generalization | — | 39.3% |
| DTBench | 59% | — |
| BIG-Bench Hard | 89.2% | — |
| ForecastBench | 58.4 | — |
Math Too close to call
Gemini 1.5 Pro (May 2024): 24.4 (#260), MiniMax-M2.7: 24.9 (#254)
| Benchmark | Gemini 1.5 Pro (May 2024) | MiniMax-M2.7 |
|---|---|---|
| LMArena Math | 1315 | 1420 |
| OTIS Mock AIME 2024-2025 | 23.1% | — |
| ProofBench | — | 3% |
| Omni-MATH | 36.4% | — |
| MATH Level 5 | 70.4% | — |
Knowledge MiniMax-M2.7 leads
Gemini 1.5 Pro (May 2024): 29.3 (#228), MiniMax-M2.7: 37.1 (#151)
| Benchmark | Gemini 1.5 Pro (May 2024) | MiniMax-M2.7 |
|---|---|---|
| LMArena Expert | 1279 | 1443 |
| GPQA Diamond | 57.2% | — |
| Humanity's Last Exam | 4.6% | — |
| MMLU-Pro | 73.7% | — |
| Confabulations | 13.5% | — |
| Vectara Hallucination Rate | — | 12.9% |
| GPQA (HELM) | 53.4% | — |
| MMLU | 86.9% | — |
Multimodal Not comparable
Gemini 1.5 Pro (May 2024): 36.2 (#72), MiniMax-M2.7: —
| Benchmark | Gemini 1.5 Pro (May 2024) | MiniMax-M2.7 |
|---|---|---|
| LMArena Vision | 1161 | — |
| Video-MME | 75% | — |
Multilingual MiniMax-M2.7 leads
Gemini 1.5 Pro (May 2024): 45.5 (#169), MiniMax-M2.7: 50.5 (#120)
| Benchmark | Gemini 1.5 Pro (May 2024) | MiniMax-M2.7 |
|---|---|---|
| LMArena Non-English | 1312 | 1382 |
| LMArena Chinese | 1331 | 1439 |
| LMArena French | 1301 | 1422 |
| LMArena German | 1286 | 1398 |
| LMArena Japanese | 1292 | 1261 |
| LMArena Korean | 1298 | 1313 |
| LMArena Russian | 1320 | 1383 |
| LMArena Spanish | 1310 | 1403 |
Instruction Following MiniMax-M2.7 leads
Gemini 1.5 Pro (May 2024): 68.8 (#180), MiniMax-M2.7: 74.2 (#101)
| Benchmark | Gemini 1.5 Pro (May 2024) | MiniMax-M2.7 |
|---|---|---|
| LMArena Instruction Following | 1297 | 1404 |
| IFEval | 83.7% | — |
Long Context MiniMax-M2.7 leads
Gemini 1.5 Pro (May 2024): 39.7 (#164), MiniMax-M2.7: 43.3 (#94)
| Benchmark | Gemini 1.5 Pro (May 2024) | MiniMax-M2.7 |
|---|---|---|
| LMArena Longer Query | 1308 | 1419 |
Writing & Preference MiniMax-M2.7 leads
Gemini 1.5 Pro (May 2024): 52.5 (#167), MiniMax-M2.7: 59.1 (#107)
| Benchmark | Gemini 1.5 Pro (May 2024) | MiniMax-M2.7 |
|---|---|---|
| LMArena Text | 1319 | 1404 |
| LMArena Creative Writing | 1333 | 1354 |
| LMArena Multi-Turn | 1296 | 1413 |
| WildBench | 81.3% | — |
Frequently asked questions
Is Gemini 1.5 Pro (May 2024) better than MiniMax-M2.7?
MiniMax-M2.7 is the stronger model overall, scoring 37.4 to 31.9 on the Noometry Index.
Is Gemini 1.5 Pro (May 2024) or MiniMax-M2.7 better for coding?
MiniMax-M2.7 scores higher on coding benchmarks: 41.4 versus 33.8 in the Noometry coding category.
How many benchmarks do Gemini 1.5 Pro (May 2024) and MiniMax-M2.7 share?
19 benchmarks have published results for both models. Gemini 1.5 Pro (May 2024) has 45 scored results on Noometry and MiniMax-M2.7 has 30.