Model comparison
Gemini 3.8 Flash vs Qwen2.5 72B Instruct
Gemini 3.8 Flash is the stronger model overall, scoring 59.5 to 31.5 on the Noometry Index.
Last verified . 22 shared benchmarks.
Google
Alibaba (Qwen)Summary
- They share 22 benchmarks with published results for both. Gemini 3.8 Flash 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 knowledge, where Gemini 3.8 Flash leads 74.9 to 26.9.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 98.9% for Gemini 3.8 Flash and 8.1% for Qwen2.5 72B Instruct.
- Gemini 3.8 Flash is cheaper at $0.75 / $3.75 per million input/output tokens, against $1.40 / $5.60 for Qwen2.5 72B Instruct.
- Gemini 3.8 Flash 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 3.8 Flash | Qwen2.5 72B Instruct | |
|---|---|---|
| Provider | Alibaba (Qwen) | |
| Noometry Index | 59.5 | 31.5 |
| Released | 2026-09-02 | 2024-09 |
| Weights | Proprietary | Open |
| Context window | 1.05M | 131K |
| Max output | 66K | 8K |
| Input $ / M tokens | $0.75 | $1.40 |
| Output $ / M tokens | $3.75 | $5.60 |
| Results tracked | 46 | 43 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemini 3.8 Flash leads
Gemini 3.8 Flash: 56.4 (#17), Qwen2.5 72B Instruct: 32.8 (#256)
| Benchmark | Gemini 3.8 Flash | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Coding | 1512 | 1293 |
| DeepSWE | 73.8% | — |
| FrontierCode | 41.2% | — |
| CursorBench | 39.6% | — |
| LMArena WebDev | 1581 | — |
| FrontierSWE | 19.6% | — |
| SciCode | 56.6% | — |
| WeirdML | — | 16% |
| BigCodeBench Instruct | — | 45.8% |
| BigCodeBench Complete | — | 55.9% |
| ALE-Bench | 1,270 | — |
Agentic & Tool Use Gemini 3.8 Flash leads
Gemini 3.8 Flash: 40.3 (#22), Qwen2.5 72B Instruct: 22.0 (#124)
| Benchmark | Gemini 3.8 Flash | Qwen2.5 72B Instruct |
|---|---|---|
| APEX-Agents | 64.3% | — |
| TheAgentCompany | — | 5.7% |
| BALROG | — | 16.2% |
| GDP.pdf | 23.4% | — |
| METR Time Horizons | — | 35.8% |
| Vending-Bench 2 | 5,094 | — |
Reasoning Gemini 3.8 Flash leads
Gemini 3.8 Flash: 64.7 (#13), Qwen2.5 72B Instruct: 21.4 (#197)
| Benchmark | Gemini 3.8 Flash | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Hard Prompts | 1506 | 1271 |
| DTBench | 95.7% | 62.9% |
| LMCA | 52.9% | 13.4% |
| Epoch Capabilities Index | 157.13 | 129.01 |
| NYT Connections (extended) | 97.4% | — |
| CritPt | 18.3% | — |
| Chess Puzzles | 61% | — |
| Mystery Game Puzzles | 47% | — |
| Surface Evolver Bench | 76.9% | — |
| BIG-Bench Hard | — | 79.8% |
| ForecastBench | — | 57.5 |
| HellaSwag | — | 84.8% |
| PIQA | — | 82.6% |
| WinoGrande | — | 82.3% |
Math Gemini 3.8 Flash leads
Gemini 3.8 Flash: 65.2 (#22), Qwen2.5 72B Instruct: 18.1 (#281)
| Benchmark | Gemini 3.8 Flash | Qwen2.5 72B Instruct |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 98.9% | 8.1% |
| LMArena Math | 1528 | 1283 |
| FrontierMath (Tiers 1-3) | 68.4% | — |
| FrontierMath Tier 4 | 22% | — |
| ProofBench | 48% | — |
| Omni-MATH | — | 33% |
| MATH Level 5 | — | 63.2% |
Knowledge Gemini 3.8 Flash leads
Gemini 3.8 Flash: 74.9 (#2), Qwen2.5 72B Instruct: 26.9 (#247)
| Benchmark | Gemini 3.8 Flash | Qwen2.5 72B Instruct |
|---|---|---|
| GPQA Diamond | 95.4% | 49.1% |
| LMArena Expert | 1529 | 1245 |
| Humanity's Last Exam | 44.5% | — |
| SimpleQA Verified | 69.7% | — |
| MMLU-Pro | — | 63.1% |
| Confabulations | — | 19.1% |
| GPQA (HELM) | — | 42.6% |
| ARC (AI2) Challenge | — | 94.5% |
| MMLU | — | 85.3% |
| TriviaQA | — | 71.9% |
Multimodal Not comparable
Gemini 3.8 Flash: 40.9 (#33), Qwen2.5 72B Instruct: —
| Benchmark | Gemini 3.8 Flash | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Vision | 1312 | — |
| Blueprint-Bench 2 | 38.6% | — |
| Furniture Assembly | 31.7% | — |
Multilingual Gemini 3.8 Flash leads
Gemini 3.8 Flash: 57.9 (#5), Qwen2.5 72B Instruct: 41.2 (#208)
| Benchmark | Gemini 3.8 Flash | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Non-English | 1486 | 1252 |
| LMArena Chinese | 1547 | 1272 |
| LMArena French | 1502 | 1279 |
| LMArena German | 1470 | 1234 |
| LMArena Japanese | 1505 | 1180 |
| LMArena Korean | 1479 | 1188 |
| LMArena Russian | 1507 | 1264 |
| LMArena Spanish | 1492 | 1255 |
Instruction Following Gemini 3.8 Flash leads
Gemini 3.8 Flash: 78.2 (#11), Qwen2.5 72B Instruct: 65.7 (#216)
| Benchmark | Gemini 3.8 Flash | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Instruction Following | 1489 | 1254 |
| IFEval | — | 80.6% |
Long Context Gemini 3.8 Flash leads
Gemini 3.8 Flash: 46.2 (#23), Qwen2.5 72B Instruct: 38.9 (#183)
| Benchmark | Gemini 3.8 Flash | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Longer Query | 1506 | 1282 |
Writing & Preference Gemini 3.8 Flash leads
Gemini 3.8 Flash: 72.1 (#16), Qwen2.5 72B Instruct: 46.9 (#210)
| Benchmark | Gemini 3.8 Flash | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Text | 1494 | 1269 |
| LMArena Creative Writing | 1485 | 1221 |
| LMArena Multi-Turn | 1503 | 1272 |
| EQ-Bench Creative Writing | 1748 | — |
| WildBench | — | 80.2% |
Frequently asked questions
Is Gemini 3.8 Flash better than Qwen2.5 72B Instruct?
Gemini 3.8 Flash is the stronger model overall, scoring 59.5 to 31.5 on the Noometry Index.
Which is cheaper, Gemini 3.8 Flash or Qwen2.5 72B Instruct?
Gemini 3.8 Flash is cheaper. It lists at $0.75 per million input tokens and $3.75 per million output tokens; Qwen2.5 72B Instruct lists at $1.40 and $5.60.
Is Gemini 3.8 Flash or Qwen2.5 72B Instruct better for coding?
Gemini 3.8 Flash scores higher on coding benchmarks: 56.4 versus 32.8 in the Noometry coding category.
Which has the bigger context window?
Gemini 3.8 Flash does, with 1.05M tokens against 131K.
How many benchmarks do Gemini 3.8 Flash and Qwen2.5 72B Instruct share?
22 benchmarks have published results for both models. Gemini 3.8 Flash has 46 scored results on Noometry and Qwen2.5 72B Instruct has 43.