Model comparison
Gemini 2.5 Pro vs Qwen3.8 27B
Gemini 2.5 Pro and Qwen3.8 27B score almost the same on the Noometry Index (45.0 vs 46.0), so choose on price, context window or the category you care about most.
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 4 categories and Qwen3.8 27B in 6 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in long context, where Gemini 2.5 Pro leads 59.8 to 44.3.
- The biggest single-benchmark swing is ARC-AGI-1: 41% for Gemini 2.5 Pro and 87.5% for Qwen3.8 27B.
- Qwen3.8 27B is cheaper at $0.99 / $1.49 per million input/output tokens, against $1.25 / $10 for Gemini 2.5 Pro.
- Gemini 2.5 Pro accepts more context: 1.05M tokens versus 262K.
- Qwen3.8 27B has downloadable open weights; the other is API-only.
Side by side
| Gemini 2.5 Pro | Qwen3.8 27B | |
|---|---|---|
| Provider | Alibaba (Qwen) | |
| Noometry Index | 45.0 | 46.0 |
| Released | 2025-03-25 | 2026-08-14 |
| Weights | Proprietary | Open |
| Context window | 1.05M | 262K |
| Max output | 66K | 33K |
| Input $ / M tokens | $1.25 | $0.99 |
| Output $ / M tokens | $10 | $1.49 |
| Results tracked | 78 | 31 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3.8 27B leads
Gemini 2.5 Pro: 42.4 (#101), Qwen3.8 27B: 50.5 (#44)
| Benchmark | Gemini 2.5 Pro | Qwen3.8 27B |
|---|---|---|
| LMArena WebDev | 1227 | 1593 |
| SciCode | 42.8% | 46.6% |
| LMArena Coding | 1452 | 1482 |
| SWE-bench Verified | 57.6% | — |
| SWE-bench Verified (bash only) | 53.6% | — |
| Aider Polyglot | 83.1% | — |
| GSO | 3.9% | — |
| WeirdML | 54% | — |
| LiveBench Coding | 85.9% | — |
| CadEval | 64% | — |
| ALE-Bench | 785.52 | — |
| AlgoTune | 1.51 | — |
Agentic & Tool Use Qwen3.8 27B leads
Gemini 2.5 Pro: 29.2 (#88), Qwen3.8 27B: 32.9 (#57)
| Benchmark | Gemini 2.5 Pro | Qwen3.8 27B |
|---|---|---|
| Terminal-Bench | 32.6% | — |
| APEX-Agents | — | 47.5% |
| 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 Qwen3.8 27B leads
Gemini 2.5 Pro: 28.8 (#99), Qwen3.8 27B: 41.0 (#54)
| Benchmark | Gemini 2.5 Pro | Qwen3.8 27B |
|---|---|---|
| ARC-AGI-2 | 4.9% | 42.4% |
| ARC-AGI-1 | 41% | 87.5% |
| CritPt | 2% | 5.4% |
| LMArena Hard Prompts | 1455 | 1460 |
| DTBench | 82.4% | 88% |
| LMCA | 34.8% | 41.4% |
| Epoch Capabilities Index | 145.32 | 149.38 |
| SimpleBench | 62.4% | — |
| Kagi LLM Benchmark | 70.3% | — |
| NYT Connections (extended) | — | 54.5% |
| Chess Puzzles | 20% | — |
| EnigmaEval | 5.6% | — |
| LiveBench Reasoning | 89.8% | — |
| LiveBench Data Analysis | 79.9% | — |
| Surface Evolver Bench | — | 45% |
| ForecastBench | 61.3 | — |
| LiveBench | 82.3% | — |
Math Qwen3.8 27B leads
Gemini 2.5 Pro: 32.5 (#213), Qwen3.8 27B: 37.1 (#161)
| Benchmark | Gemini 2.5 Pro | Qwen3.8 27B |
|---|---|---|
| LMArena Math | 1450 | 1456 |
| FrontierMath (Tiers 1-3) | 24.6% | — |
| FrontierMath Tier 4 | 0% | — |
| OTIS Mock AIME 2024-2025 | 84.7% | — |
| ProofBench | — | 16% |
| Omni-MATH | 41.6% | — |
| LiveBench Math | 90.2% | — |
| 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: 56.0 (#46), Qwen3.8 27B: 41.6 (#109)
| Benchmark | Gemini 2.5 Pro | Qwen3.8 27B |
|---|---|---|
| LMArena Expert | 1452 | 1482 |
| GPQA Diamond | 85.3% | — |
| Humanity's Last Exam | 21.6% | — |
| MMLU-Pro | 86.3% | — |
| Confabulations | 10.6% | — |
| Vectara Hallucination Rate | 7% | — |
| GPQA (HELM) | 74.9% | — |
Multimodal Gemini 2.5 Pro leads
Gemini 2.5 Pro: 45.2 (#18), Qwen3.8 27B: 41.3 (#37)
| Benchmark | Gemini 2.5 Pro | Qwen3.8 27B |
|---|---|---|
| LMArena Vision | 1263 | 1271 |
| GeoBench | 86% | — |
| VPCT | 48% | — |
| LMArena Document | 1421 | — |
| SpatialViz-Bench | 44.7% | — |
Multilingual Gemini 2.5 Pro leads
Gemini 2.5 Pro: 55.3 (#31), Qwen3.8 27B: 53.7 (#60)
| Benchmark | Gemini 2.5 Pro | Qwen3.8 27B |
|---|---|---|
| LMArena Non-English | 1451 | 1430 |
| LMArena Chinese | 1507 | 1504 |
| LMArena French | 1472 | 1465 |
| LMArena German | 1487 | 1438 |
| LMArena Japanese | 1461 | 1384 |
| LMArena Korean | 1434 | 1393 |
| LMArena Russian | 1461 | 1415 |
| LMArena Spanish | 1473 | 1448 |
Instruction Following Too close to call
Gemini 2.5 Pro: 75.0 (#75), Qwen3.8 27B: 75.8 (#53)
| Benchmark | Gemini 2.5 Pro | Qwen3.8 27B |
|---|---|---|
| LMArena Instruction Following | 1437 | 1439 |
| LiveBench Instruction Following | 80.6% | — |
| IFEval | 84% | — |
Long Context Gemini 2.5 Pro leads
Gemini 2.5 Pro: 59.8 (#5), Qwen3.8 27B: 44.3 (#70)
| Benchmark | Gemini 2.5 Pro | Qwen3.8 27B |
|---|---|---|
| LMArena Longer Query | 1449 | 1450 |
| Fiction.LiveBench | 91.7% | — |
Writing & Preference Qwen3.8 27B leads
Gemini 2.5 Pro: 63.7 (#62), Qwen3.8 27B: 65.8 (#43)
| Benchmark | Gemini 2.5 Pro | Qwen3.8 27B |
|---|---|---|
| LMArena Text | 1458 | 1441 |
| LMArena Creative Writing | 1454 | 1384 |
| EQ-Bench Creative Writing | 1421 | 1671 |
| LMArena Multi-Turn | 1453 | 1441 |
| Short-Story Creative Writing | 83.8% | — |
| WildBench | 85.7% | — |
| LiveBench Language | 67.8% | — |
Frequently asked questions
Is Gemini 2.5 Pro better than Qwen3.8 27B?
Gemini 2.5 Pro and Qwen3.8 27B score almost the same on the Noometry Index (45.0 vs 46.0), so choose on price, context window or the category you care about most.
Which is cheaper, Gemini 2.5 Pro or Qwen3.8 27B?
Qwen3.8 27B is cheaper. It lists at $0.99 per million input tokens and $1.49 per million output tokens; Gemini 2.5 Pro lists at $1.25 and $10.
Is Gemini 2.5 Pro or Qwen3.8 27B better for coding?
Qwen3.8 27B scores higher on coding benchmarks: 50.5 versus 42.4 in the Noometry coding category.
Which has the bigger context window?
Gemini 2.5 Pro does, with 1.05M tokens against 262K.
How many benchmarks do Gemini 2.5 Pro and Qwen3.8 27B share?
27 benchmarks have published results for both models. Gemini 2.5 Pro has 78 scored results on Noometry and Qwen3.8 27B has 31.