Model comparison
Gemini 1.5 Pro (May 2024) vs MiniMax-M2.5
MiniMax-M2.5 is the stronger model overall, scoring 38.3 to 32.1 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 1 category and MiniMax-M2.5 in 8 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in coding, where MiniMax-M2.5 leads 48.1 to 34.2.
- MiniMax-M2.5 has downloadable open weights; the other is API-only.
Side by side
| Gemini 1.5 Pro (May 2024) | MiniMax-M2.5 | |
|---|---|---|
| Provider | MiniMax | |
| Noometry Index | 32.1 | 38.3 |
| Released | 2024-02-15 | 2026-02-12 |
| Weights | Proprietary | Open |
| Context window | — | 205K |
| Max output | — | 131K |
| Input $ / M tokens | — | $0.30 |
| Output $ / M tokens | — | $1.20 |
| Results tracked | 45 | 33 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiniMax-M2.5 leads
Gemini 1.5 Pro (May 2024): 34.2 (#241), MiniMax-M2.5: 48.1 (#58)
| Benchmark | Gemini 1.5 Pro (May 2024) | MiniMax-M2.5 |
|---|---|---|
| LMArena Coding | 1294 | 1381 |
| SWE-bench Verified (bash only) | — | 75.8% |
| LMArena WebDev | — | 1387 |
| SWE-bench Multilingual | — | 68.3% |
| WeirdML | 22.2% | — |
| BigCodeBench Instruct | 43.8% | — |
| BigCodeBench Complete | 57.5% | — |
| CadEval | 34% | — |
| ALE-Bench | — | 618.17 |
| HumanEval+ | 79.3% | — |
| MBPP+ | 74.6% | — |
Agentic & Tool Use MiniMax-M2.5 leads
Gemini 1.5 Pro (May 2024): 17.9 (#145), MiniMax-M2.5: 30.4 (#77)
| Benchmark | Gemini 1.5 Pro (May 2024) | MiniMax-M2.5 |
|---|---|---|
| Terminal-Bench | — | 42.7% |
| TheAgentCompany | 3.4% | — |
| Cybench | 7.5% | — |
| BALROG | 21% | — |
| Vending-Bench 2 | — | -23.16 |
Reasoning MiniMax-M2.5 leads
Gemini 1.5 Pro (May 2024): 12.3 (#338), MiniMax-M2.5: 17.5 (#292)
| Benchmark | Gemini 1.5 Pro (May 2024) | MiniMax-M2.5 |
|---|---|---|
| ARC-AGI-2 | 0.8% | 4.9% |
| LMArena Hard Prompts | 1296 | 1372 |
| Epoch Capabilities Index | 131.73 | 146.68 |
| SimpleBench | 27.1% | — |
| Kagi LLM Benchmark | — | 55.2% |
| NYT Connections (extended) | — | 16.8% |
| ARC-AGI-1 | — | 63.7% |
| DTBench | 59% | — |
| BIG-Bench Hard | 89.2% | — |
| ForecastBench | 58.4 | — |
Math MiniMax-M2.5 leads
Gemini 1.5 Pro (May 2024): 25.8 (#266), MiniMax-M2.5: 26.9 (#253)
| Benchmark | Gemini 1.5 Pro (May 2024) | MiniMax-M2.5 |
|---|---|---|
| LMArena Math | 1315 | 1378 |
| OTIS Mock AIME 2024-2025 | 23.1% | — |
| ProofBench | — | 4% |
| Omni-MATH | 36.4% | — |
| MATH Level 5 | 70.4% | — |
Knowledge MiniMax-M2.5 leads
Gemini 1.5 Pro (May 2024): 29.4 (#239), MiniMax-M2.5: 39.2 (#135)
| Benchmark | Gemini 1.5 Pro (May 2024) | MiniMax-M2.5 |
|---|---|---|
| LMArena Expert | 1279 | 1379 |
| GPQA Diamond | 57.2% | — |
| Humanity's Last Exam | 4.6% | — |
| MMLU-Pro | 73.7% | — |
| Confabulations | 13.5% | — |
| Vectara Hallucination Rate | — | 9.1% |
| GPQA (HELM) | 53.4% | — |
| MMLU | 86.9% | — |
Multimodal Not comparable
Gemini 1.5 Pro (May 2024): 36.8 (#77), MiniMax-M2.5: —
| Benchmark | Gemini 1.5 Pro (May 2024) | MiniMax-M2.5 |
|---|---|---|
| LMArena Vision | 1161 | — |
| Video-MME | 75% | — |
Multilingual MiniMax-M2.5 leads
Gemini 1.5 Pro (May 2024): 45.3 (#174), MiniMax-M2.5: 47.1 (#152)
| Benchmark | Gemini 1.5 Pro (May 2024) | MiniMax-M2.5 |
|---|---|---|
| LMArena Non-English | 1312 | 1338 |
| LMArena Chinese | 1331 | 1393 |
| LMArena French | 1302 | 1362 |
| LMArena German | 1286 | 1362 |
| LMArena Japanese | 1292 | 1171 |
| LMArena Korean | 1298 | 1232 |
| LMArena Russian | 1320 | 1358 |
| LMArena Spanish | 1311 | 1354 |
Instruction Following MiniMax-M2.5 leads
Gemini 1.5 Pro (May 2024): 68.6 (#185), MiniMax-M2.5: 71.5 (#148)
| Benchmark | Gemini 1.5 Pro (May 2024) | MiniMax-M2.5 |
|---|---|---|
| LMArena Instruction Following | 1297 | 1353 |
| IFEval | 83.7% | — |
Long Context Gemini 1.5 Pro (May 2024) leads
Gemini 1.5 Pro (May 2024): 39.8 (#169), MiniMax-M2.5: 37.5 (#216)
| Benchmark | Gemini 1.5 Pro (May 2024) | MiniMax-M2.5 |
|---|---|---|
| LMArena Longer Query | 1308 | 1366 |
| CL-bench | — | 11.4% |
| CL-bench Life | — | 6.3% |
Writing & Preference MiniMax-M2.5 leads
Gemini 1.5 Pro (May 2024): 52.4 (#172), MiniMax-M2.5: 53.9 (#153)
| Benchmark | Gemini 1.5 Pro (May 2024) | MiniMax-M2.5 |
|---|---|---|
| LMArena Text | 1319 | 1359 |
| LMArena Creative Writing | 1333 | 1331 |
| LMArena Multi-Turn | 1296 | 1364 |
| EQ-Bench Creative Writing | — | 1361 |
| WildBench | 81.3% | — |
Frequently asked questions
Is Gemini 1.5 Pro (May 2024) better than MiniMax-M2.5?
MiniMax-M2.5 is the stronger model overall, scoring 38.3 to 32.1 on the Noometry Index.
Is Gemini 1.5 Pro (May 2024) or MiniMax-M2.5 better for coding?
MiniMax-M2.5 scores higher on coding benchmarks: 48.1 versus 34.2 in the Noometry coding category.
How many benchmarks do Gemini 1.5 Pro (May 2024) and MiniMax-M2.5 share?
19 benchmarks have published results for both models. Gemini 1.5 Pro (May 2024) has 45 scored results on Noometry and MiniMax-M2.5 has 33.