Model comparison
GPT-5 Nano vs Qwen2.5 Plus 1127
Qwen2.5 Plus 1127 is the stronger model overall, scoring 38.1 to 33.4 on the Noometry Index.
Last verified . 13 shared benchmarks.
Alibaba (Qwen)Summary
- They share 13 benchmarks with published results for both. GPT-5 Nano scores higher in 3 categories and Qwen2.5 Plus 1127 in 5 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Qwen2.5 Plus 1127 leads 49.5 to 39.4.
Side by side
| GPT-5 Nano | Qwen2.5 Plus 1127 | |
|---|---|---|
| Provider | OpenAI | Alibaba (Qwen) |
| Noometry Index | 33.4 | 38.1 |
| Released | 2025-08-07 | — |
| Weights | Proprietary | Proprietary |
| Context window | 400K | — |
| Max output | 128K | — |
| Input $ / M tokens | $0.05 | — |
| Output $ / M tokens | $0.40 | — |
| Results tracked | 48 | 14 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen2.5 Plus 1127 leads
GPT-5 Nano: 33.3 (#248), Qwen2.5 Plus 1127: 37.9 (#171)
| Benchmark | GPT-5 Nano | Qwen2.5 Plus 1127 |
|---|---|---|
| LMArena Coding | 1351 | 1314 |
| SWE-bench Verified (bash only) | 34.8% | — |
| WeirdML | 38.1% | — |
| ALE-Bench | 718.67 | — |
Agentic & Tool Use Not comparable
GPT-5 Nano: 25.6 (#99), Qwen2.5 Plus 1127: —
| Benchmark | GPT-5 Nano | Qwen2.5 Plus 1127 |
|---|---|---|
| Terminal-Bench | 21.8% | — |
| Berkeley Function Calling Leaderboard | 51.5% | — |
Reasoning Qwen2.5 Plus 1127 leads
GPT-5 Nano: 16.4 (#291), Qwen2.5 Plus 1127: 24.8 (#139)
| Benchmark | GPT-5 Nano | Qwen2.5 Plus 1127 |
|---|---|---|
| LMArena Hard Prompts | 1329 | 1299 |
| ARC-AGI-2 | 2.6% | — |
| Kagi LLM Benchmark | 62.2% | — |
| ARC-AGI-1 | 20.7% | — |
| Chess Puzzles | 27% | — |
| Mystery Game Puzzles | 9% | — |
| DTBench | 62.7% | — |
| LMCA | 7.9% | — |
| Epoch Capabilities Index | 139.39 | — |
| ForecastBench | 59.1 | — |
Math Qwen2.5 Plus 1127 leads
GPT-5 Nano: 29.1 (#221), Qwen2.5 Plus 1127: 33.5 (#175)
| Benchmark | GPT-5 Nano | Qwen2.5 Plus 1127 |
|---|---|---|
| LMArena Math | 1318 | 1298 |
| FrontierMath (Tiers 1-3) | 20% | — |
| FrontierMath Tier 4 | 2.4% | — |
| OTIS Mock AIME 2024-2025 | 81.1% | — |
| ProofBench | 12% | — |
| Omni-MATH | 54.6% | — |
| MATH Level 5 | 95.2% | — |
| FrontierMath (Feb 2025 set) | 8.3% | — |
| FrontierMath Tier 4 (v1) | 2.1% | — |
Knowledge Too close to call
GPT-5 Nano: 35.8 (#166), Qwen2.5 Plus 1127: 34.9 (#179)
| Benchmark | GPT-5 Nano | Qwen2.5 Plus 1127 |
|---|---|---|
| LMArena Expert | 1321 | 1289 |
| GPQA Diamond | 69.4% | — |
| SimpleQA Verified | 11.7% | — |
| MMLU-Pro | 77.8% | — |
| Vectara Hallucination Rate | 10.5% | — |
| GPQA (HELM) | 67.9% | — |
Multimodal Not comparable
GPT-5 Nano: 30.7 (#102), Qwen2.5 Plus 1127: —
| Benchmark | GPT-5 Nano | Qwen2.5 Plus 1127 |
|---|---|---|
| LMArena Vision | 1159 | — |
| VPCT | 37.2% | — |
Multilingual GPT-5 Nano leads
GPT-5 Nano: 45.5 (#167), Qwen2.5 Plus 1127: 42.1 (#196)
| Benchmark | GPT-5 Nano | Qwen2.5 Plus 1127 |
|---|---|---|
| LMArena Non-English | 1313 | 1265 |
| LMArena Chinese | 1355 | 1314 |
| LMArena German | 1329 | 1231 |
| LMArena Russian | 1296 | 1271 |
| LMArena Japanese | — | 1207 |
| LMArena Korean | 1269 | — |
| LMArena Spanish | 1360 | — |
Instruction Following GPT-5 Nano leads
GPT-5 Nano: 75.2 (#72), Qwen2.5 Plus 1127: 67.4 (#194)
| Benchmark | GPT-5 Nano | Qwen2.5 Plus 1127 |
|---|---|---|
| LMArena Instruction Following | 1306 | 1275 |
| IFEval | 93.2% | — |
Long Context Qwen2.5 Plus 1127 leads
GPT-5 Nano: 31.3 (#275), Qwen2.5 Plus 1127: 39.2 (#180)
| Benchmark | GPT-5 Nano | Qwen2.5 Plus 1127 |
|---|---|---|
| LMArena Longer Query | 1313 | 1292 |
| Fiction.LiveBench | 44.4% | — |
Writing & Preference Qwen2.5 Plus 1127 leads
GPT-5 Nano: 39.4 (#244), Qwen2.5 Plus 1127: 49.5 (#186)
| Benchmark | GPT-5 Nano | Qwen2.5 Plus 1127 |
|---|---|---|
| LMArena Text | 1320 | 1299 |
| LMArena Creative Writing | 1250 | 1262 |
| LMArena Multi-Turn | 1311 | 1299 |
| EQ-Bench Creative Writing | 705 | — |
| WildBench | 80.6% | — |
Frequently asked questions
Is GPT-5 Nano better than Qwen2.5 Plus 1127?
Qwen2.5 Plus 1127 is the stronger model overall, scoring 38.1 to 33.4 on the Noometry Index.
Is GPT-5 Nano or Qwen2.5 Plus 1127 better for coding?
Qwen2.5 Plus 1127 scores higher on coding benchmarks: 37.9 versus 33.3 in the Noometry coding category.
How many benchmarks do GPT-5 Nano and Qwen2.5 Plus 1127 share?
13 benchmarks have published results for both models. GPT-5 Nano has 48 scored results on Noometry and Qwen2.5 Plus 1127 has 14.