Model comparison
GPT-5 Nano vs Qwen2.5 72B Instruct
GPT-5 Nano is the stronger model overall, scoring 33.4 to 31.5 on the Noometry Index.
Last verified . 28 shared benchmarks.
Alibaba (Qwen)Summary
- They share 28 benchmarks with published results for both. GPT-5 Nano scores higher in 6 categories and Qwen2.5 72B Instruct in 3 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where GPT-5 Nano leads 29.1 to 18.1.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 81.1% for GPT-5 Nano and 8.1% for Qwen2.5 72B Instruct.
- GPT-5 Nano is cheaper at $0.05 / $0.40 per million input/output tokens, against $1.40 / $5.60 for Qwen2.5 72B Instruct.
- GPT-5 Nano accepts more context: 400K tokens versus 131K.
- Qwen2.5 72B Instruct has downloadable open weights; the other is API-only.
Side by side
| GPT-5 Nano | Qwen2.5 72B Instruct | |
|---|---|---|
| Provider | OpenAI | Alibaba (Qwen) |
| Noometry Index | 33.4 | 31.5 |
| Released | 2025-08-07 | 2024-09 |
| Weights | Proprietary | Open |
| Context window | 400K | 131K |
| Max output | 128K | 8K |
| Input $ / M tokens | $0.05 | $1.40 |
| Output $ / M tokens | $0.40 | $5.60 |
| Results tracked | 48 | 43 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
GPT-5 Nano: 33.3 (#248), Qwen2.5 72B Instruct: 32.8 (#256)
| Benchmark | GPT-5 Nano | Qwen2.5 72B Instruct |
|---|---|---|
| WeirdML | 38.1% | 16% |
| LMArena Coding | 1351 | 1293 |
| SWE-bench Verified (bash only) | 34.8% | — |
| BigCodeBench Instruct | — | 45.8% |
| BigCodeBench Complete | — | 55.9% |
| ALE-Bench | 718.67 | — |
Agentic & Tool Use GPT-5 Nano leads
GPT-5 Nano: 25.6 (#99), Qwen2.5 72B Instruct: 22.0 (#124)
| Benchmark | GPT-5 Nano | Qwen2.5 72B Instruct |
|---|---|---|
| Terminal-Bench | 21.8% | — |
| Berkeley Function Calling Leaderboard | 51.5% | — |
| TheAgentCompany | — | 5.7% |
| BALROG | — | 16.2% |
| METR Time Horizons | — | 35.8% |
Reasoning Qwen2.5 72B Instruct leads
GPT-5 Nano: 16.4 (#291), Qwen2.5 72B Instruct: 21.4 (#197)
| Benchmark | GPT-5 Nano | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Hard Prompts | 1329 | 1271 |
| DTBench | 62.7% | 62.9% |
| LMCA | 7.9% | 13.4% |
| Epoch Capabilities Index | 139.39 | 129.01 |
| ForecastBench | 59.1 | 57.5 |
| ARC-AGI-2 | 2.6% | — |
| Kagi LLM Benchmark | 62.2% | — |
| ARC-AGI-1 | 20.7% | — |
| Chess Puzzles | 27% | — |
| Mystery Game Puzzles | 9% | — |
| BIG-Bench Hard | — | 79.8% |
| HellaSwag | — | 84.8% |
| PIQA | — | 82.6% |
| WinoGrande | — | 82.3% |
Math GPT-5 Nano leads
GPT-5 Nano: 29.1 (#221), Qwen2.5 72B Instruct: 18.1 (#281)
| Benchmark | GPT-5 Nano | Qwen2.5 72B Instruct |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 81.1% | 8.1% |
| Omni-MATH | 54.6% | 33% |
| LMArena Math | 1318 | 1283 |
| MATH Level 5 | 95.2% | 63.2% |
| FrontierMath (Tiers 1-3) | 20% | — |
| FrontierMath Tier 4 | 2.4% | — |
| ProofBench | 12% | — |
| FrontierMath (Feb 2025 set) | 8.3% | — |
| FrontierMath Tier 4 (v1) | 2.1% | — |
Knowledge GPT-5 Nano leads
GPT-5 Nano: 35.8 (#166), Qwen2.5 72B Instruct: 26.9 (#247)
| Benchmark | GPT-5 Nano | Qwen2.5 72B Instruct |
|---|---|---|
| GPQA Diamond | 69.4% | 49.1% |
| MMLU-Pro | 77.8% | 63.1% |
| GPQA (HELM) | 67.9% | 42.6% |
| LMArena Expert | 1321 | 1245 |
| SimpleQA Verified | 11.7% | — |
| Confabulations | — | 19.1% |
| Vectara Hallucination Rate | 10.5% | — |
| ARC (AI2) Challenge | — | 94.5% |
| MMLU | — | 85.3% |
| TriviaQA | — | 71.9% |
Multimodal Not comparable
GPT-5 Nano: 30.7 (#102), Qwen2.5 72B Instruct: —
| Benchmark | GPT-5 Nano | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Vision | 1159 | — |
| VPCT | 37.2% | — |
Multilingual GPT-5 Nano leads
GPT-5 Nano: 45.5 (#167), Qwen2.5 72B Instruct: 41.2 (#208)
| Benchmark | GPT-5 Nano | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Non-English | 1313 | 1252 |
| LMArena Chinese | 1355 | 1272 |
| LMArena German | 1329 | 1234 |
| LMArena Korean | 1269 | 1188 |
| LMArena Russian | 1296 | 1264 |
| LMArena Spanish | 1360 | 1255 |
| LMArena French | — | 1279 |
| LMArena Japanese | — | 1180 |
Instruction Following GPT-5 Nano leads
GPT-5 Nano: 75.2 (#72), Qwen2.5 72B Instruct: 65.7 (#216)
| Benchmark | GPT-5 Nano | Qwen2.5 72B Instruct |
|---|---|---|
| IFEval | 93.2% | 80.6% |
| LMArena Instruction Following | 1306 | 1254 |
Long Context Qwen2.5 72B Instruct leads
GPT-5 Nano: 31.3 (#275), Qwen2.5 72B Instruct: 38.9 (#183)
| Benchmark | GPT-5 Nano | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Longer Query | 1313 | 1282 |
| Fiction.LiveBench | 44.4% | — |
Writing & Preference Qwen2.5 72B Instruct leads
GPT-5 Nano: 39.4 (#244), Qwen2.5 72B Instruct: 46.9 (#210)
| Benchmark | GPT-5 Nano | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Text | 1320 | 1269 |
| LMArena Creative Writing | 1250 | 1221 |
| WildBench | 80.6% | 80.2% |
| LMArena Multi-Turn | 1311 | 1272 |
| EQ-Bench Creative Writing | 705 | — |
Frequently asked questions
Is GPT-5 Nano better than Qwen2.5 72B Instruct?
GPT-5 Nano is the stronger model overall, scoring 33.4 to 31.5 on the Noometry Index.
Which is cheaper, GPT-5 Nano or Qwen2.5 72B Instruct?
GPT-5 Nano is cheaper. It lists at $0.05 per million input tokens and $0.40 per million output tokens; Qwen2.5 72B Instruct lists at $1.40 and $5.60.
Is GPT-5 Nano or Qwen2.5 72B Instruct better for coding?
They score almost the same on coding (33.3 vs 32.8); test both on your own repository before choosing.
Which has the bigger context window?
GPT-5 Nano does, with 400K tokens against 131K.
How many benchmarks do GPT-5 Nano and Qwen2.5 72B Instruct share?
28 benchmarks have published results for both models. GPT-5 Nano has 48 scored results on Noometry and Qwen2.5 72B Instruct has 43.