Model comparison
GPT-4.5 vs Qwen3.5 122B-A10B
Qwen3.5 122B-A10B is the stronger model overall, scoring 42.1 to 37.2 on the Noometry Index.
Last verified . 17 shared benchmarks.
Alibaba (Qwen)Summary
- They share 17 benchmarks with published results for both. GPT-4.5 scores higher in 2 categories and Qwen3.5 122B-A10B in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Qwen3.5 122B-A10B leads 27.2 to 13.9.
- Qwen3.5 122B-A10B has downloadable open weights; the other is API-only.
Side by side
| GPT-4.5 | Qwen3.5 122B-A10B | |
|---|---|---|
| Provider | OpenAI | Alibaba (Qwen) |
| Noometry Index | 37.2 | 42.1 |
| Released | 2025-02-27 | 2026-02-23 |
| Weights | Proprietary | Open |
| Context window | — | 262K |
| Max output | — | 66K |
| Input $ / M tokens | — | $0.40 |
| Output $ / M tokens | — | $3.20 |
| Results tracked | 42 | 27 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-4.5 leads
GPT-4.5: 42.2 (#109), Qwen3.5 122B-A10B: 39.1 (#162)
| Benchmark | GPT-4.5 | Qwen3.5 122B-A10B |
|---|---|---|
| LMArena Coding | 1396 | 1436 |
| Aider Polyglot | 44.9% | — |
| LMArena WebDev | — | 1360 |
| SciCode | — | 35.6% |
| WeirdML | 39.4% | — |
| LiveBench Coding | 75.2% | — |
Agentic & Tool Use Not comparable
GPT-4.5: 27.9 (#97), Qwen3.5 122B-A10B: —
| Benchmark | GPT-4.5 | Qwen3.5 122B-A10B |
|---|---|---|
| Cybench | 17.5% | — |
Reasoning Qwen3.5 122B-A10B leads
GPT-4.5: 13.9 (#330), Qwen3.5 122B-A10B: 27.2 (#123)
| Benchmark | GPT-4.5 | Qwen3.5 122B-A10B |
|---|---|---|
| LMArena Hard Prompts | 1403 | 1421 |
| ARC-AGI-2 | 0.8% | — |
| SimpleBench | 34.5% | — |
| NYT Connections (extended) | — | 51.7% |
| ARC-AGI-1 | 10.3% | — |
| CritPt | — | 0.9% |
| EnigmaEval | 3.2% | — |
| Thematic Generalization | — | 51.2% |
| LiveBench Reasoning | 71.1% | — |
| Mystery Game Puzzles | — | 17% |
| DTBench | — | 84.3% |
| LiveBench Data Analysis | 64.3% | — |
| LMCA | — | 32.2% |
| Epoch Capabilities Index | 136.74 | — |
| ForecastBench | 61.7 | — |
| LiveBench | 69% | — |
Math Qwen3.5 122B-A10B leads
GPT-4.5: 32.6 (#211), Qwen3.5 122B-A10B: 39.1 (#112)
| Benchmark | GPT-4.5 | Qwen3.5 122B-A10B |
|---|---|---|
| LMArena Math | 1412 | 1432 |
| OTIS Mock AIME 2024-2025 | 37.8% | — |
| LiveBench Math | 69.3% | — |
| MATH Level 5 | 78.6% | — |
Knowledge Qwen3.5 122B-A10B leads
GPT-4.5: 32.5 (#211), Qwen3.5 122B-A10B: 38.8 (#142)
| Benchmark | GPT-4.5 | Qwen3.5 122B-A10B |
|---|---|---|
| LMArena Expert | 1394 | 1432 |
| GPQA Diamond | 68.7% | — |
| Humanity's Last Exam | 5.4% | — |
| Confabulations | 13.6% | — |
| Vectara Hallucination Rate | — | 11.2% |
Multimodal Qwen3.5 122B-A10B leads
GPT-4.5: 37.6 (#71), Qwen3.5 122B-A10B: 39.6 (#57)
| Benchmark | GPT-4.5 | Qwen3.5 122B-A10B |
|---|---|---|
| LMArena Vision | 1195 | 1245 |
| VPCT | 45% | — |
Multilingual Too close to call
GPT-4.5: 52.5 (#83), Qwen3.5 122B-A10B: 51.6 (#107)
| Benchmark | GPT-4.5 | Qwen3.5 122B-A10B |
|---|---|---|
| LMArena Non-English | 1413 | 1400 |
| LMArena Chinese | 1421 | 1462 |
| LMArena French | 1418 | 1442 |
| LMArena German | 1457 | 1426 |
| LMArena Japanese | 1416 | 1367 |
| LMArena Korean | 1392 | 1352 |
| LMArena Russian | 1419 | 1400 |
| LMArena Spanish | — | 1424 |
Instruction Following Qwen3.5 122B-A10B leads
GPT-4.5: 72.6 (#134), Qwen3.5 122B-A10B: 73.8 (#115)
| Benchmark | GPT-4.5 | Qwen3.5 122B-A10B |
|---|---|---|
| LMArena Instruction Following | 1404 | 1399 |
| LiveBench Instruction Following | 72.3% | — |
Long Context Qwen3.5 122B-A10B leads
GPT-4.5: 40.4 (#155), Qwen3.5 122B-A10B: 43.0 (#109)
| Benchmark | GPT-4.5 | Qwen3.5 122B-A10B |
|---|---|---|
| LMArena Longer Query | 1406 | 1410 |
| Fiction.LiveBench | 63.9% | — |
Writing & Preference Qwen3.5 122B-A10B leads
GPT-4.5: 56.9 (#134), Qwen3.5 122B-A10B: 60.0 (#105)
| Benchmark | GPT-4.5 | Qwen3.5 122B-A10B |
|---|---|---|
| LMArena Text | 1417 | 1417 |
| LMArena Creative Writing | 1394 | 1368 |
| LMArena Multi-Turn | 1444 | 1416 |
| Short-Story Creative Writing | 75.6% | — |
| EQ-Bench Creative Writing | 1258 | — |
| LiveBench Language | 61.5% | — |
Frequently asked questions
Is GPT-4.5 better than Qwen3.5 122B-A10B?
Qwen3.5 122B-A10B is the stronger model overall, scoring 42.1 to 37.2 on the Noometry Index.
Is GPT-4.5 or Qwen3.5 122B-A10B better for coding?
GPT-4.5 scores higher on coding benchmarks: 42.2 versus 39.1 in the Noometry coding category.
How many benchmarks do GPT-4.5 and Qwen3.5 122B-A10B share?
17 benchmarks have published results for both models. GPT-4.5 has 42 scored results on Noometry and Qwen3.5 122B-A10B has 27.