Model comparison
Gemini 3.1 Pro Preview vs Qwen2.5-Max
Gemini 3.1 Pro Preview is the stronger model overall, scoring 56.7 to 40.1 on the Noometry Index.
Last verified . 18 shared benchmarks.
Google
Alibaba (Qwen)Summary
- They share 18 benchmarks with published results for both. Gemini 3.1 Pro Preview scores higher in 8 categories and Qwen2.5-Max in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Gemini 3.1 Pro Preview leads 71.7 to 24.6.
Side by side
| Gemini 3.1 Pro Preview | Qwen2.5-Max | |
|---|---|---|
| Provider | Alibaba (Qwen) | |
| Noometry Index | 56.7 | 40.1 |
| Released | 2026-02-19 | 2025-01-25 |
| Weights | Proprietary | Proprietary |
| Context window | 1.05M | — |
| Max output | 66K | — |
| Input $ / M tokens | $2 | — |
| Output $ / M tokens | $12 | — |
| Results tracked | 71 | 27 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemini 3.1 Pro Preview leads
Gemini 3.1 Pro Preview: 42.7 (#88), Qwen2.5-Max: 41.2 (#118)
| Benchmark | Gemini 3.1 Pro Preview | Qwen2.5-Max |
|---|---|---|
| LMArena Coding | 1483 | 1359 |
| SWE-bench Verified | 75.6% | — |
| DeepSWE | 11.7% | — |
| LMArena WebDev | 1446 | — |
| SciCode | 58.9% | — |
| GSO | 22.6% | — |
| WeirdML | 72.1% | — |
| LiveBench Coding | — | 64.4% |
| MirrorCode | 8.9% | — |
| ALE-Bench | 1,161 | — |
| AlgoTune | 2.02 | — |
Agentic & Tool Use Not comparable
Gemini 3.1 Pro Preview: 37.7 (#33), Qwen2.5-Max: —
| Benchmark | Gemini 3.1 Pro Preview | Qwen2.5-Max |
|---|---|---|
| Terminal-Bench | 80.2% | — |
| APEX-Agents | 35.3% | — |
| τ²-bench Banking | 26% | — |
| DeepResearch Bench | 47.8% | — |
| PostTrainBench | 22% | — |
| BALROG | 57% | — |
| ExploitBench | 26.1% | — |
| GBAEval | 0.8% | — |
| GDP.pdf | 17% | — |
| LMArena Search | 1211 | — |
| METR Time Horizons | 77% | — |
| Vending-Bench 2 | 3,774 | — |
Reasoning Gemini 3.1 Pro Preview leads
Gemini 3.1 Pro Preview: 71.7 (#9), Qwen2.5-Max: 24.6 (#144)
| Benchmark | Gemini 3.1 Pro Preview | Qwen2.5-Max |
|---|---|---|
| LMArena Hard Prompts | 1484 | 1360 |
| Epoch Capabilities Index | 154.92 | 132.54 |
| ARC-AGI-2 | 77.1% | — |
| SimpleBench | 79.6% | — |
| NYT Connections (extended) | 97.4% | — |
| ARC-AGI-1 | 98% | — |
| CritPt | 17.7% | — |
| Chess Puzzles | 55% | — |
| EnigmaEval | 36.8% | — |
| Thematic Generalization | 79.4% | — |
| EBR-Bench | 14.3% | — |
| LiveBench Reasoning | — | 51.4% |
| Mystery Game Puzzles | 34% | — |
| DTBench | 97.1% | — |
| LiveBench Data Analysis | — | 67.9% |
| LMCA | 53.8% | — |
| ForecastBench | 59 | — |
| LiveBench | — | 62.3% |
Math Gemini 3.1 Pro Preview leads
Gemini 3.1 Pro Preview: 61.8 (#28), Qwen2.5-Max: 34.3 (#162)
| Benchmark | Gemini 3.1 Pro Preview | Qwen2.5-Max |
|---|---|---|
| LMArena Math | 1485 | 1369 |
| FrontierMath (Tiers 1-3) | 59.6% | — |
| FrontierMath Tier 4 | 26.8% | — |
| MathArena Final-Answer Competitions | 86.5% | — |
| OTIS Mock AIME 2024-2025 | 95.6% | — |
| ProofBench | 26% | — |
| LiveBench Math | — | 58.4% |
| FrontierMath (Feb 2025 set) | 36.9% | — |
| FrontierMath Tier 4 (v1) | 16.7% | — |
Knowledge Gemini 3.1 Pro Preview leads
Gemini 3.1 Pro Preview: 71.8 (#3), Qwen2.5-Max: 34.8 (#181)
| Benchmark | Gemini 3.1 Pro Preview | Qwen2.5-Max |
|---|---|---|
| LMArena Expert | 1484 | 1337 |
| GPQA Diamond | 94.4% | — |
| Humanity's Last Exam | 46.4% | — |
| SimpleQA Verified | 73.5% | — |
| Confabulations | — | 21.8% |
| Vectara Hallucination Rate | 10.4% | — |
Multimodal Not comparable
Gemini 3.1 Pro Preview: 38.1 (#60), Qwen2.5-Max: —
| Benchmark | Gemini 3.1 Pro Preview | Qwen2.5-Max |
|---|---|---|
| LMArena Vision | 1296 | — |
| Blueprint-Bench 2 | 26.5% | — |
| Furniture Assembly | 26.7% | — |
| LMArena Document | 1444 | — |
Multilingual Gemini 3.1 Pro Preview leads
Gemini 3.1 Pro Preview: 57.1 (#11), Qwen2.5-Max: 48.3 (#140)
| Benchmark | Gemini 3.1 Pro Preview | Qwen2.5-Max |
|---|---|---|
| LMArena Non-English | 1475 | 1352 |
| LMArena Chinese | 1528 | 1382 |
| LMArena French | 1488 | 1396 |
| LMArena German | 1491 | 1350 |
| LMArena Japanese | 1494 | 1299 |
| LMArena Korean | 1458 | 1304 |
| LMArena Russian | 1496 | 1353 |
| LMArena Spanish | 1480 | 1377 |
Instruction Following Gemini 3.1 Pro Preview leads
Gemini 3.1 Pro Preview: 77.1 (#31), Qwen2.5-Max: 71.5 (#147)
| Benchmark | Gemini 3.1 Pro Preview | Qwen2.5-Max |
|---|---|---|
| LMArena Instruction Following | 1465 | 1335 |
| LiveBench Instruction Following | — | 75.3% |
Long Context Gemini 3.1 Pro Preview leads
Gemini 3.1 Pro Preview: 47.3 (#17), Qwen2.5-Max: 41.3 (#137)
| Benchmark | Gemini 3.1 Pro Preview | Qwen2.5-Max |
|---|---|---|
| LMArena Longer Query | 1482 | 1358 |
| CL-bench | 20.8% | — |
| CL-bench Life | 16.9% | — |
Writing & Preference Gemini 3.1 Pro Preview leads
Gemini 3.1 Pro Preview: 66.3 (#36), Qwen2.5-Max: 55.6 (#141)
| Benchmark | Gemini 3.1 Pro Preview | Qwen2.5-Max |
|---|---|---|
| LMArena Text | 1480 | 1367 |
| LMArena Creative Writing | 1482 | 1339 |
| LMArena Multi-Turn | 1486 | 1364 |
| Short-Story Creative Writing | — | 72.9% |
| EQ-Bench Creative Writing | 1491 | — |
| EQ-Bench 4 | 1142 | — |
| LiveBench Language | — | 56.3% |
Frequently asked questions
Is Gemini 3.1 Pro Preview better than Qwen2.5-Max?
Gemini 3.1 Pro Preview is the stronger model overall, scoring 56.7 to 40.1 on the Noometry Index.
Is Gemini 3.1 Pro Preview or Qwen2.5-Max better for coding?
Gemini 3.1 Pro Preview scores higher on coding benchmarks: 42.7 versus 41.2 in the Noometry coding category.
How many benchmarks do Gemini 3.1 Pro Preview and Qwen2.5-Max share?
18 benchmarks have published results for both models. Gemini 3.1 Pro Preview has 71 scored results on Noometry and Qwen2.5-Max has 27.