Model comparison
GPT-4.5 vs Qwen3-Next 80B-A3B Instruct
Qwen3-Next 80B-A3B Instruct is the stronger model overall, scoring 42.5 to 36.9 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 3 categories and Qwen3-Next 80B-A3B Instruct in 5 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Qwen3-Next 80B-A3B Instruct leads 30.1 to 14.1.
- The biggest single-benchmark swing is Fiction.LiveBench: 63.9% for GPT-4.5 and 55.6% for Qwen3-Next 80B-A3B Instruct.
- Qwen3-Next 80B-A3B Instruct has downloadable open weights; the other is API-only.
Side by side
| GPT-4.5 | Qwen3-Next 80B-A3B Instruct | |
|---|---|---|
| Provider | OpenAI | Alibaba (Qwen) |
| Noometry Index | 36.9 | 42.5 |
| Released | 2025-02-27 | 2025-09 |
| Weights | Proprietary | Open |
| Context window | — | 131K |
| Max output | — | 33K |
| Input $ / M tokens | — | $0.50 |
| Output $ / M tokens | — | $2 |
| Results tracked | 42 | 25 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
GPT-4.5: 41.8 (#102), Qwen3-Next 80B-A3B Instruct: 41.9 (#101)
| Benchmark | GPT-4.5 | Qwen3-Next 80B-A3B Instruct |
|---|---|---|
| LMArena Coding | 1397 | 1441 |
| Aider Polyglot | 44.9% | — |
| WeirdML | 39.4% | — |
| LiveBench Coding | 75.2% | — |
Agentic & Tool Use Not comparable
GPT-4.5: 27.6 (#92), Qwen3-Next 80B-A3B Instruct: —
| Benchmark | GPT-4.5 | Qwen3-Next 80B-A3B Instruct |
|---|---|---|
| Cybench | 17.5% | — |
Reasoning Qwen3-Next 80B-A3B Instruct leads
GPT-4.5: 14.1 (#320), Qwen3-Next 80B-A3B Instruct: 30.1 (#79)
| Benchmark | GPT-4.5 | Qwen3-Next 80B-A3B Instruct |
|---|---|---|
| LMArena Hard Prompts | 1404 | 1428 |
| ARC-AGI-2 | 0.8% | — |
| SimpleBench | 34.5% | — |
| Kagi LLM Benchmark | — | 66.7% |
| ARC-AGI-1 | 10.3% | — |
| EnigmaEval | 3.2% | — |
| LiveBench Reasoning | 71.1% | — |
| LiveBench Data Analysis | 64.3% | — |
| Epoch Capabilities Index | 136.74 | — |
| ForecastBench | 61.7 | — |
| LiveBench | 69% | — |
Math Qwen3-Next 80B-A3B Instruct leads
GPT-4.5: 31.0 (#200), Qwen3-Next 80B-A3B Instruct: 36.3 (#118)
| Benchmark | GPT-4.5 | Qwen3-Next 80B-A3B Instruct |
|---|---|---|
| LMArena Math | 1412 | 1440 |
| OTIS Mock AIME 2024-2025 | 37.8% | — |
| Omni-MATH | — | 46.7% |
| LiveBench Math | 69.3% | — |
| MATH Level 5 | 78.6% | — |
Knowledge Qwen3-Next 80B-A3B Instruct leads
GPT-4.5: 32.4 (#205), Qwen3-Next 80B-A3B Instruct: 41.3 (#102)
| Benchmark | GPT-4.5 | Qwen3-Next 80B-A3B Instruct |
|---|---|---|
| LMArena Expert | 1394 | 1416 |
| GPQA Diamond | 68.7% | — |
| Humanity's Last Exam | 5.4% | — |
| MMLU-Pro | — | 78.6% |
| Confabulations | 13.6% | — |
| Vectara Hallucination Rate | — | 9.3% |
| GPQA (HELM) | — | 63% |
Multimodal Not comparable
GPT-4.5: 37.0 (#68), Qwen3-Next 80B-A3B Instruct: —
| Benchmark | GPT-4.5 | Qwen3-Next 80B-A3B Instruct |
|---|---|---|
| LMArena Vision | 1195 | — |
| VPCT | 45% | — |
Multilingual Too close to call
GPT-4.5: 52.7 (#78), Qwen3-Next 80B-A3B Instruct: 52.3 (#88)
| Benchmark | GPT-4.5 | Qwen3-Next 80B-A3B Instruct |
|---|---|---|
| LMArena Non-English | 1413 | 1407 |
| LMArena Chinese | 1421 | 1461 |
| LMArena French | 1417 | 1415 |
| LMArena German | 1457 | 1416 |
| LMArena Japanese | 1416 | 1398 |
| LMArena Korean | 1392 | 1366 |
| LMArena Russian | 1419 | 1403 |
| LMArena Spanish | — | 1436 |
Instruction Following GPT-4.5 leads
GPT-4.5: 72.8 (#129), Qwen3-Next 80B-A3B Instruct: 71.0 (#154)
| Benchmark | GPT-4.5 | Qwen3-Next 80B-A3B Instruct |
|---|---|---|
| LMArena Instruction Following | 1404 | 1388 |
| LiveBench Instruction Following | 72.3% | — |
| IFEval | — | 81% |
Long Context GPT-4.5 leads
GPT-4.5: 40.4 (#150), Qwen3-Next 80B-A3B Instruct: 37.0 (#218)
| Benchmark | GPT-4.5 | Qwen3-Next 80B-A3B Instruct |
|---|---|---|
| Fiction.LiveBench | 63.9% | 55.6% |
| LMArena Longer Query | 1406 | 1403 |
Writing & Preference Qwen3-Next 80B-A3B Instruct leads
GPT-4.5: 57.1 (#129), Qwen3-Next 80B-A3B Instruct: 58.2 (#116)
| Benchmark | GPT-4.5 | Qwen3-Next 80B-A3B Instruct |
|---|---|---|
| LMArena Text | 1417 | 1417 |
| LMArena Creative Writing | 1394 | 1333 |
| LMArena Multi-Turn | 1444 | 1415 |
| Short-Story Creative Writing | 75.6% | — |
| EQ-Bench Creative Writing | 1258 | — |
| WildBench | — | 80.7% |
| LiveBench Language | 61.5% | — |
Frequently asked questions
Is GPT-4.5 better than Qwen3-Next 80B-A3B Instruct?
Qwen3-Next 80B-A3B Instruct is the stronger model overall, scoring 42.5 to 36.9 on the Noometry Index.
Is GPT-4.5 or Qwen3-Next 80B-A3B Instruct better for coding?
They score almost the same on coding (41.8 vs 41.9); test both on your own repository before choosing.
How many benchmarks do GPT-4.5 and Qwen3-Next 80B-A3B Instruct share?
17 benchmarks have published results for both models. GPT-4.5 has 42 scored results on Noometry and Qwen3-Next 80B-A3B Instruct has 25.