Model comparison
Gemini 2.5 Pro vs Qwen2.5-Max
Gemini 2.5 Pro is the stronger model overall, scoring 44.9 to 40.1 on the Noometry Index.
Last verified . 27 shared benchmarks.
Google
Alibaba (Qwen)Summary
- They share 27 benchmarks with published results for both. Gemini 2.5 Pro scores higher in 7 categories and Qwen2.5-Max in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Gemini 2.5 Pro leads 55.8 to 34.8.
- The biggest single-benchmark swing is LiveBench Reasoning: 89.8% for Gemini 2.5 Pro and 51.4% for Qwen2.5-Max.
Side by side
| Gemini 2.5 Pro | Qwen2.5-Max | |
|---|---|---|
| Provider | Alibaba (Qwen) | |
| Noometry Index | 44.9 | 40.1 |
| Released | 2025-03-25 | 2025-01-25 |
| Weights | Proprietary | Proprietary |
| Context window | 1.05M | — |
| Max output | 66K | — |
| Input $ / M tokens | $1.25 | — |
| Output $ / M tokens | $10 | — |
| Results tracked | 78 | 27 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemini 2.5 Pro leads
Gemini 2.5 Pro: 42.8 (#86), Qwen2.5-Max: 41.2 (#118)
| Benchmark | Gemini 2.5 Pro | Qwen2.5-Max |
|---|---|---|
| LiveBench Coding | 85.9% | 64.4% |
| LMArena Coding | 1452 | 1359 |
| SWE-bench Verified | 57.6% | — |
| SWE-bench Verified (bash only) | 53.6% | — |
| Aider Polyglot | 83.1% | — |
| LMArena WebDev | 1227 | — |
| SciCode | 42.8% | — |
| GSO | 3.9% | — |
| WeirdML | 54% | — |
| CadEval | 64% | — |
| ALE-Bench | 785.52 | — |
| AlgoTune | 1.51 | — |
Agentic & Tool Use Not comparable
Gemini 2.5 Pro: 29.1 (#81), Qwen2.5-Max: —
| Benchmark | Gemini 2.5 Pro | Qwen2.5-Max |
|---|---|---|
| Terminal-Bench | 32.6% | — |
| GDPval | 23.3% | — |
| Remote Labor Index | 0.8% | — |
| TheAgentCompany | 30.3% | — |
| τ²-bench Banking | 13.7% | — |
| DeepResearch Bench | 42.8% | — |
| BALROG | 43.3% | — |
| LMArena Search | 1142 | — |
| METR Time Horizons | 55.4% | — |
| Vending-Bench 2 | 573.64 | — |
Reasoning Gemini 2.5 Pro leads
Gemini 2.5 Pro: 28.8 (#85), Qwen2.5-Max: 24.6 (#144)
| Benchmark | Gemini 2.5 Pro | Qwen2.5-Max |
|---|---|---|
| LiveBench Reasoning | 89.8% | 51.4% |
| LMArena Hard Prompts | 1455 | 1360 |
| LiveBench Data Analysis | 79.9% | 67.9% |
| Epoch Capabilities Index | 145.32 | 132.54 |
| LiveBench | 82.3% | 62.3% |
| ARC-AGI-2 | 4.9% | — |
| SimpleBench | 62.4% | — |
| Kagi LLM Benchmark | 70.3% | — |
| ARC-AGI-1 | 41% | — |
| CritPt | 2% | — |
| Chess Puzzles | 20% | — |
| EnigmaEval | 5.6% | — |
| DTBench | 82.4% | — |
| LMCA | 34.8% | — |
| ForecastBench | 61.3 | — |
Math Qwen2.5-Max leads
Gemini 2.5 Pro: 31.9 (#191), Qwen2.5-Max: 34.3 (#162)
| Benchmark | Gemini 2.5 Pro | Qwen2.5-Max |
|---|---|---|
| LiveBench Math | 90.2% | 58.4% |
| LMArena Math | 1450 | 1369 |
| FrontierMath (Tiers 1-3) | 24.6% | — |
| FrontierMath Tier 4 | 0% | — |
| OTIS Mock AIME 2024-2025 | 84.7% | — |
| Omni-MATH | 41.6% | — |
| MATH Level 5 | 95.9% | — |
| FrontierMath (Feb 2025 set) | 14.1% | — |
| FrontierMath Tier 4 (v1) | 4.2% | — |
Knowledge Gemini 2.5 Pro leads
Gemini 2.5 Pro: 55.8 (#41), Qwen2.5-Max: 34.8 (#181)
| Benchmark | Gemini 2.5 Pro | Qwen2.5-Max |
|---|---|---|
| Confabulations | 10.6% | 21.8% |
| LMArena Expert | 1452 | 1337 |
| GPQA Diamond | 85.3% | — |
| Humanity's Last Exam | 21.6% | — |
| MMLU-Pro | 86.3% | — |
| Vectara Hallucination Rate | 7% | — |
| GPQA (HELM) | 74.9% | — |
Multimodal Not comparable
Gemini 2.5 Pro: 44.5 (#16), Qwen2.5-Max: —
| Benchmark | Gemini 2.5 Pro | Qwen2.5-Max |
|---|---|---|
| LMArena Vision | 1263 | — |
| GeoBench | 86% | — |
| VPCT | 48% | — |
| LMArena Document | 1421 | — |
| SpatialViz-Bench | 44.7% | — |
Multilingual Gemini 2.5 Pro leads
Gemini 2.5 Pro: 55.5 (#30), Qwen2.5-Max: 48.3 (#140)
| Benchmark | Gemini 2.5 Pro | Qwen2.5-Max |
|---|---|---|
| LMArena Non-English | 1452 | 1352 |
| LMArena Chinese | 1507 | 1382 |
| LMArena French | 1473 | 1396 |
| LMArena German | 1487 | 1350 |
| LMArena Japanese | 1462 | 1299 |
| LMArena Korean | 1435 | 1304 |
| LMArena Russian | 1460 | 1353 |
| LMArena Spanish | 1473 | 1377 |
Instruction Following Gemini 2.5 Pro leads
Gemini 2.5 Pro: 75.2 (#71), Qwen2.5-Max: 71.5 (#147)
| Benchmark | Gemini 2.5 Pro | Qwen2.5-Max |
|---|---|---|
| LiveBench Instruction Following | 80.6% | 75.3% |
| LMArena Instruction Following | 1436 | 1335 |
| IFEval | 84% | — |
Long Context Gemini 2.5 Pro leads
Gemini 2.5 Pro: 59.7 (#5), Qwen2.5-Max: 41.3 (#137)
| Benchmark | Gemini 2.5 Pro | Qwen2.5-Max |
|---|---|---|
| LMArena Longer Query | 1449 | 1358 |
| Fiction.LiveBench | 91.7% | — |
Writing & Preference Gemini 2.5 Pro leads
Gemini 2.5 Pro: 63.9 (#60), Qwen2.5-Max: 55.6 (#141)
| Benchmark | Gemini 2.5 Pro | Qwen2.5-Max |
|---|---|---|
| LMArena Text | 1458 | 1367 |
| LMArena Creative Writing | 1453 | 1339 |
| Short-Story Creative Writing | 83.8% | 72.9% |
| LMArena Multi-Turn | 1453 | 1364 |
| LiveBench Language | 67.8% | 56.3% |
| EQ-Bench Creative Writing | 1421 | — |
| WildBench | 85.7% | — |
Frequently asked questions
Is Gemini 2.5 Pro better than Qwen2.5-Max?
Gemini 2.5 Pro is the stronger model overall, scoring 44.9 to 40.1 on the Noometry Index.
Is Gemini 2.5 Pro or Qwen2.5-Max better for coding?
Gemini 2.5 Pro scores higher on coding benchmarks: 42.8 versus 41.2 in the Noometry coding category.
How many benchmarks do Gemini 2.5 Pro and Qwen2.5-Max share?
27 benchmarks have published results for both models. Gemini 2.5 Pro has 78 scored results on Noometry and Qwen2.5-Max has 27.