Model comparison
Gemini 1.5 Pro (May 2024) vs MiniMax-M3
MiniMax-M3 is the stronger model overall, scoring 43.8 to 32.1 on the Noometry Index.
Last verified . 24 shared benchmarks.
Google
MiniMaxSummary
- They share 24 benchmarks with published results for both. Gemini 1.5 Pro (May 2024) scores higher in 0 categories and MiniMax-M3 in 10 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where MiniMax-M3 leads 58.4 to 29.4.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 23.1% for Gemini 1.5 Pro (May 2024) and 71.1% for MiniMax-M3.
- MiniMax-M3 has downloadable open weights; the other is API-only.
Side by side
| Gemini 1.5 Pro (May 2024) | MiniMax-M3 | |
|---|---|---|
| Provider | MiniMax | |
| Noometry Index | 32.1 | 43.8 |
| Released | 2024-02-15 | 2026-06-01 |
| Weights | Proprietary | Open |
| Context window | — | 1M |
| Max output | — | 512K |
| Input $ / M tokens | — | $0.30 |
| Output $ / M tokens | — | $1.20 |
| Results tracked | 45 | 41 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiniMax-M3 leads
Gemini 1.5 Pro (May 2024): 34.2 (#241), MiniMax-M3: 41.8 (#118)
| Benchmark | Gemini 1.5 Pro (May 2024) | MiniMax-M3 |
|---|---|---|
| LMArena Coding | 1294 | 1469 |
| FrontierCode | — | 14.7% |
| LMArena WebDev | — | 1482 |
| SciCode | — | 47.1% |
| WeirdML | 22.2% | — |
| BigCodeBench Instruct | 43.8% | — |
| BigCodeBench Complete | 57.5% | — |
| CadEval | 34% | — |
| ALE-Bench | — | 640.02 |
| HumanEval+ | 79.3% | — |
| MBPP+ | 74.6% | — |
Agentic & Tool Use MiniMax-M3 leads
Gemini 1.5 Pro (May 2024): 17.9 (#145), MiniMax-M3: 22.6 (#130)
| Benchmark | Gemini 1.5 Pro (May 2024) | MiniMax-M3 |
|---|---|---|
| APEX-Agents | — | 37.7% |
| OSWorld 2.0 | — | 4.6% |
| TheAgentCompany | 3.4% | — |
| Cybench | 7.5% | — |
| BALROG | 21% | — |
| GBAEval | — | 0.9% |
| Vending-Bench 2 | — | 2,158 |
Reasoning MiniMax-M3 leads
Gemini 1.5 Pro (May 2024): 12.3 (#338), MiniMax-M3: 30.1 (#87)
| Benchmark | Gemini 1.5 Pro (May 2024) | MiniMax-M3 |
|---|---|---|
| SimpleBench | 27.1% | 45.8% |
| LMArena Hard Prompts | 1296 | 1447 |
| DTBench | 59% | 78.9% |
| Epoch Capabilities Index | 131.73 | 146.95 |
| ForecastBench | 58.4 | 61.4 |
| ARC-AGI-2 | 0.8% | — |
| NYT Connections (extended) | — | 65.1% |
| CritPt | — | 3.7% |
| Chess Puzzles | — | 14% |
| Mystery Game Puzzles | — | 8% |
| LMCA | — | 33.7% |
| Surface Evolver Bench | — | 55% |
| BIG-Bench Hard | 89.2% | — |
Math MiniMax-M3 leads
Gemini 1.5 Pro (May 2024): 25.8 (#266), MiniMax-M3: 40.0 (#95)
| Benchmark | Gemini 1.5 Pro (May 2024) | MiniMax-M3 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 23.1% | 71.1% |
| LMArena Math | 1315 | 1429 |
| ProofBench | — | 18% |
| Omni-MATH | 36.4% | — |
| MATH Level 5 | 70.4% | — |
Knowledge MiniMax-M3 leads
Gemini 1.5 Pro (May 2024): 29.4 (#239), MiniMax-M3: 58.4 (#35)
| Benchmark | Gemini 1.5 Pro (May 2024) | MiniMax-M3 |
|---|---|---|
| GPQA Diamond | 57.2% | 90.9% |
| LMArena Expert | 1279 | 1461 |
| Humanity's Last Exam | 4.6% | — |
| MMLU-Pro | 73.7% | — |
| Confabulations | 13.5% | — |
| GPQA (HELM) | 53.4% | — |
| MMLU | 86.9% | — |
Multimodal MiniMax-M3 leads
Gemini 1.5 Pro (May 2024): 36.8 (#77), MiniMax-M3: 40.2 (#51)
| Benchmark | Gemini 1.5 Pro (May 2024) | MiniMax-M3 |
|---|---|---|
| LMArena Vision | 1161 | 1253 |
| Video-MME | 75% | — |
| LMArena Document | — | 1435 |
Multilingual MiniMax-M3 leads
Gemini 1.5 Pro (May 2024): 45.3 (#174), MiniMax-M3: 53.0 (#75)
| Benchmark | Gemini 1.5 Pro (May 2024) | MiniMax-M3 |
|---|---|---|
| LMArena Non-English | 1312 | 1420 |
| LMArena Chinese | 1331 | 1463 |
| LMArena French | 1302 | 1447 |
| LMArena German | 1286 | 1426 |
| LMArena Japanese | 1292 | 1381 |
| LMArena Korean | 1298 | 1372 |
| LMArena Russian | 1320 | 1428 |
| LMArena Spanish | 1311 | 1432 |
Instruction Following MiniMax-M3 leads
Gemini 1.5 Pro (May 2024): 68.6 (#185), MiniMax-M3: 75.5 (#62)
| Benchmark | Gemini 1.5 Pro (May 2024) | MiniMax-M3 |
|---|---|---|
| LMArena Instruction Following | 1297 | 1433 |
| IFEval | 83.7% | — |
Long Context MiniMax-M3 leads
Gemini 1.5 Pro (May 2024): 39.8 (#169), MiniMax-M3: 44.2 (#72)
| Benchmark | Gemini 1.5 Pro (May 2024) | MiniMax-M3 |
|---|---|---|
| LMArena Longer Query | 1308 | 1445 |
Writing & Preference MiniMax-M3 leads
Gemini 1.5 Pro (May 2024): 52.4 (#172), MiniMax-M3: 62.1 (#83)
| Benchmark | Gemini 1.5 Pro (May 2024) | MiniMax-M3 |
|---|---|---|
| LMArena Text | 1319 | 1433 |
| LMArena Creative Writing | 1333 | 1404 |
| LMArena Multi-Turn | 1296 | 1442 |
| WildBench | 81.3% | — |
| EQ-Bench 4 | — | 1150 |
Frequently asked questions
Is Gemini 1.5 Pro (May 2024) better than MiniMax-M3?
MiniMax-M3 is the stronger model overall, scoring 43.8 to 32.1 on the Noometry Index.
Is Gemini 1.5 Pro (May 2024) or MiniMax-M3 better for coding?
MiniMax-M3 scores higher on coding benchmarks: 41.8 versus 34.2 in the Noometry coding category.
How many benchmarks do Gemini 1.5 Pro (May 2024) and MiniMax-M3 share?
24 benchmarks have published results for both models. Gemini 1.5 Pro (May 2024) has 45 scored results on Noometry and MiniMax-M3 has 41.