Model comparison
Gemini 3.1 Pro Preview vs Qwen2.5 72B Instruct
Gemini 3.1 Pro Preview is the stronger model overall, scoring 56.7 to 31.9 on the Noometry Index. Qwen2.5 72B Instruct costs 1.8× less per token, which makes it the better buy when Gemini 3.1 Pro Preview's lead doesn't matter for your workload.
Last verified . 26 shared benchmarks.
Google
Alibaba (Qwen)Summary
- They share 26 benchmarks with published results for both. Gemini 3.1 Pro Preview scores higher in 9 categories and Qwen2.5 72B Instruct in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Gemini 3.1 Pro Preview leads 71.7 to 22.3.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 95.6% for Gemini 3.1 Pro Preview and 8.1% for Qwen2.5 72B Instruct.
- Qwen2.5 72B Instruct is cheaper at $1.40 / $5.60 per million input/output tokens, against $2 / $12 for Gemini 3.1 Pro Preview.
- Gemini 3.1 Pro Preview accepts more context: 1.05M tokens versus 131K.
- Qwen2.5 72B Instruct has downloadable open weights; the other is API-only.
Side by side
| Gemini 3.1 Pro Preview | Qwen2.5 72B Instruct | |
|---|---|---|
| Provider | Alibaba (Qwen) | |
| Noometry Index | 56.7 | 31.9 |
| Released | 2026-02-19 | 2024-09 |
| Weights | Proprietary | Open |
| Context window | 1.05M | 131K |
| Max output | 66K | 8K |
| Input $ / M tokens | $2 | $1.40 |
| Output $ / M tokens | $12 | $5.60 |
| Results tracked | 71 | 43 |
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: 42.5 (#99), Qwen2.5 72B Instruct: 33.2 (#260)
| Benchmark | Gemini 3.1 Pro Preview | Qwen2.5 72B Instruct |
|---|---|---|
| WeirdML | 72.1% | 16% |
| LMArena Coding | 1484 | 1292 |
| SWE-bench Verified | 75.6% | — |
| DeepSWE | 11.7% | — |
| LMArena WebDev | 1447 | — |
| SciCode | 58.9% | — |
| GSO | 22.6% | — |
| BigCodeBench Instruct | — | 45.8% |
| MirrorCode | 8.9% | — |
| BigCodeBench Complete | — | 55.9% |
| ALE-Bench | 1,161 | — |
| AlgoTune | 2.02 | — |
Agentic & Tool Use Gemini 3.1 Pro Preview leads
Gemini 3.1 Pro Preview: 37.7 (#34), Qwen2.5 72B Instruct: 22.1 (#133)
| Benchmark | Gemini 3.1 Pro Preview | Qwen2.5 72B Instruct |
|---|---|---|
| BALROG | 57% | 16.2% |
| METR Time Horizons | 77% | 35.8% |
| Terminal-Bench | 80.2% | — |
| APEX-Agents | 35.3% | — |
| TheAgentCompany | — | 5.7% |
| τ²-bench Banking | 26% | — |
| DeepResearch Bench | 47.8% | — |
| PostTrainBench | 22% | — |
| ExploitBench | 26.1% | — |
| GBAEval | 0.8% | — |
| GDP.pdf | 17% | — |
| LMArena Search | 1211 | — |
| Vending-Bench 2 | 3,774 | — |
Reasoning Gemini 3.1 Pro Preview leads
Gemini 3.1 Pro Preview: 71.7 (#12), Qwen2.5 72B Instruct: 22.3 (#199)
| Benchmark | Gemini 3.1 Pro Preview | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Hard Prompts | 1485 | 1271 |
| DTBench | 97.1% | 62.9% |
| LMCA | 53.8% | 13.4% |
| Epoch Capabilities Index | 154.77 | 129 |
| ForecastBench | 59 | 57.5 |
| 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% | — |
| Mystery Game Puzzles | 34% | — |
| BIG-Bench Hard | — | 79.8% |
| HellaSwag | — | 84.8% |
| PIQA | — | 82.6% |
| WinoGrande | — | 82.3% |
Math Gemini 3.1 Pro Preview leads
Gemini 3.1 Pro Preview: 62.1 (#34), Qwen2.5 72B Instruct: 19.3 (#287)
| Benchmark | Gemini 3.1 Pro Preview | Qwen2.5 72B Instruct |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 95.6% | 8.1% |
| LMArena Math | 1485 | 1283 |
| FrontierMath (Tiers 1-3) | 59.6% | — |
| FrontierMath Tier 4 | 26.8% | — |
| MathArena Final-Answer Competitions | 86.5% | — |
| ProofBench | 26% | — |
| Omni-MATH | — | 33% |
| MATH Level 5 | — | 63.2% |
| 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 72B Instruct: 27.0 (#253)
| Benchmark | Gemini 3.1 Pro Preview | Qwen2.5 72B Instruct |
|---|---|---|
| GPQA Diamond | 94.4% | 49.1% |
| LMArena Expert | 1485 | 1245 |
| Humanity's Last Exam | 46.4% | — |
| SimpleQA Verified | 73.5% | — |
| MMLU-Pro | — | 63.1% |
| Confabulations | — | 19.1% |
| Vectara Hallucination Rate | 10.4% | — |
| GPQA (HELM) | — | 42.6% |
| ARC (AI2) Challenge | — | 94.5% |
| MMLU | — | 85.3% |
| TriviaQA | — | 71.9% |
Multimodal Not comparable
Gemini 3.1 Pro Preview: 37.9 (#69), Qwen2.5 72B Instruct: —
| Benchmark | Gemini 3.1 Pro Preview | Qwen2.5 72B Instruct |
|---|---|---|
| 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: 57.0 (#12), Qwen2.5 72B Instruct: 41.0 (#213)
| Benchmark | Gemini 3.1 Pro Preview | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Non-English | 1477 | 1252 |
| LMArena Chinese | 1529 | 1272 |
| LMArena French | 1487 | 1280 |
| LMArena German | 1491 | 1234 |
| LMArena Japanese | 1493 | 1180 |
| LMArena Korean | 1455 | 1188 |
| LMArena Russian | 1498 | 1264 |
| LMArena Spanish | 1479 | 1256 |
Instruction Following Gemini 3.1 Pro Preview leads
Gemini 3.1 Pro Preview: 77.0 (#32), Qwen2.5 72B Instruct: 65.5 (#221)
| Benchmark | Gemini 3.1 Pro Preview | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Instruction Following | 1466 | 1254 |
| IFEval | — | 80.6% |
Long Context Gemini 3.1 Pro Preview leads
Gemini 3.1 Pro Preview: 47.4 (#18), Qwen2.5 72B Instruct: 38.9 (#188)
| Benchmark | Gemini 3.1 Pro Preview | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Longer Query | 1483 | 1282 |
| CL-bench | 20.8% | — |
| CL-bench Life | 16.9% | — |
Writing & Preference Gemini 3.1 Pro Preview leads
Gemini 3.1 Pro Preview: 66.1 (#37), Qwen2.5 72B Instruct: 46.7 (#215)
| Benchmark | Gemini 3.1 Pro Preview | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Text | 1481 | 1269 |
| LMArena Creative Writing | 1482 | 1221 |
| LMArena Multi-Turn | 1488 | 1272 |
| EQ-Bench Creative Writing | 1491 | — |
| WildBench | — | 80.2% |
| EQ-Bench 4 | 1142 | — |
Frequently asked questions
Is Gemini 3.1 Pro Preview better than Qwen2.5 72B Instruct?
Gemini 3.1 Pro Preview is the stronger model overall, scoring 56.7 to 31.9 on the Noometry Index. Qwen2.5 72B Instruct costs 1.8× less per token, which makes it the better buy when Gemini 3.1 Pro Preview's lead doesn't matter for your workload.
Which is cheaper, Gemini 3.1 Pro Preview or Qwen2.5 72B Instruct?
Qwen2.5 72B Instruct is cheaper. It lists at $1.40 per million input tokens and $5.60 per million output tokens; Gemini 3.1 Pro Preview lists at $2 and $12.
Is Gemini 3.1 Pro Preview or Qwen2.5 72B Instruct better for coding?
Gemini 3.1 Pro Preview scores higher on coding benchmarks: 42.5 versus 33.2 in the Noometry coding category.
Which has the bigger context window?
Gemini 3.1 Pro Preview does, with 1.05M tokens against 131K.
How many benchmarks do Gemini 3.1 Pro Preview and Qwen2.5 72B Instruct share?
26 benchmarks have published results for both models. Gemini 3.1 Pro Preview has 71 scored results on Noometry and Qwen2.5 72B Instruct has 43.