Model comparison
GPT-4 vs Qwen3-Coder 480B-A35B Instruct
Qwen3-Coder 480B-A35B Instruct is the stronger model overall, scoring 38.1 to 29.1 on the Noometry Index.
Last verified . 18 shared benchmarks.
Alibaba (Qwen)Summary
- They share 18 benchmarks with published results for both. GPT-4 scores higher in 0 categories and Qwen3-Coder 480B-A35B Instruct in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen3-Coder 480B-A35B Instruct leads 37.6 to 10.8.
- The biggest single-benchmark swing is WeirdML: 12.4% for GPT-4 and 41.2% for Qwen3-Coder 480B-A35B Instruct.
- Qwen3-Coder 480B-A35B Instruct is cheaper at $1.50 / $7.50 per million input/output tokens, against $30 / $60 for GPT-4.
- Qwen3-Coder 480B-A35B Instruct accepts more context: 262K tokens versus 8K.
- Qwen3-Coder 480B-A35B Instruct has downloadable open weights; the other is API-only.
Side by side
| GPT-4 | Qwen3-Coder 480B-A35B Instruct | |
|---|---|---|
| Provider | OpenAI | Alibaba (Qwen) |
| Noometry Index | 29.1 | 38.1 |
| Released | 2023-03-14 | 2025-04 |
| Weights | Proprietary | Open |
| Context window | 8K | 262K |
| Max output | 8K | 66K |
| Input $ / M tokens | $30 | $1.50 |
| Output $ / M tokens | $60 | $7.50 |
| Results tracked | 38 | 25 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3-Coder 480B-A35B Instruct leads
GPT-4: 31.6 (#283), Qwen3-Coder 480B-A35B Instruct: 35.5 (#223)
| Benchmark | GPT-4 | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| WeirdML | 12.4% | 41.2% |
| LMArena Coding | 1254 | 1412 |
| SWE-bench Verified (bash only) | — | 55.4% |
| LMArena WebDev | — | 1275 |
| GSO | — | 4.9% |
| BigCodeBench Instruct | 46% | — |
| BigCodeBench Complete | 57.2% | — |
| ALE-Bench | — | 461.45 |
| AlgoTune | — | 1.44 |
| HumanEval+ | 79.3% | — |
Agentic & Tool Use Not comparable
GPT-4: —, Qwen3-Coder 480B-A35B Instruct: 23.9 (#123)
| Benchmark | GPT-4 | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| Terminal-Bench | — | 27.2% |
| METR Time Horizons | 36.1% | — |
Reasoning Qwen3-Coder 480B-A35B Instruct leads
GPT-4: 17.8 (#289), Qwen3-Coder 480B-A35B Instruct: 25.5 (#149)
| Benchmark | GPT-4 | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Hard Prompts | 1241 | 1372 |
| Kagi LLM Benchmark | — | 49.5% |
| Chess Puzzles | 4% | — |
| Mystery Game Puzzles | 12% | — |
| DTBench | 62.7% | — |
| LMCA | 17.1% | — |
| BIG-Bench Hard | 75.1% | — |
| Epoch Capabilities Index | 125.89 | — |
| ForecastBench | 57.8 | — |
| HellaSwag | 95.3% | — |
| WinoGrande | 87.5% | — |
Math Qwen3-Coder 480B-A35B Instruct leads
GPT-4: 10.8 (#309), Qwen3-Coder 480B-A35B Instruct: 37.6 (#150)
| Benchmark | GPT-4 | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Math | 1269 | 1365 |
| OTIS Mock AIME 2024-2025 | 1.1% | — |
| MATH Level 5 | 23% | — |
| GSM8K | 92% | — |
Knowledge Qwen3-Coder 480B-A35B Instruct leads
GPT-4: 18.4 (#282), Qwen3-Coder 480B-A35B Instruct: 37.0 (#162)
| Benchmark | GPT-4 | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Expert | 1211 | 1338 |
| GPQA Diamond | 35.7% | — |
| MMLU | 86.4% | — |
| TriviaQA | 84.8% | — |
Multilingual Qwen3-Coder 480B-A35B Instruct leads
GPT-4: 40.6 (#215), Qwen3-Coder 480B-A35B Instruct: 47.7 (#148)
| Benchmark | GPT-4 | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Non-English | 1246 | 1346 |
| LMArena Chinese | 1242 | 1357 |
| LMArena French | 1283 | 1398 |
| LMArena German | 1251 | 1325 |
| LMArena Japanese | 1209 | 1310 |
| LMArena Korean | 1184 | 1305 |
| LMArena Russian | 1251 | 1366 |
| LMArena Spanish | 1261 | 1360 |
Instruction Following Qwen3-Coder 480B-A35B Instruct leads
GPT-4: 65.3 (#222), Qwen3-Coder 480B-A35B Instruct: 71.6 (#147)
| Benchmark | GPT-4 | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Instruction Following | 1241 | 1355 |
Long Context Qwen3-Coder 480B-A35B Instruct leads
GPT-4: 37.7 (#212), Qwen3-Coder 480B-A35B Instruct: 42.0 (#131)
| Benchmark | GPT-4 | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Longer Query | 1244 | 1378 |
Writing & Preference Qwen3-Coder 480B-A35B Instruct leads
GPT-4: 34.9 (#268), Qwen3-Coder 480B-A35B Instruct: 55.3 (#147)
| Benchmark | GPT-4 | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Text | 1263 | 1357 |
| LMArena Creative Writing | 1244 | 1333 |
| LMArena Multi-Turn | 1257 | 1365 |
| EQ-Bench Creative Writing | 752 | — |
Frequently asked questions
Is GPT-4 better than Qwen3-Coder 480B-A35B Instruct?
Qwen3-Coder 480B-A35B Instruct is the stronger model overall, scoring 38.1 to 29.1 on the Noometry Index.
Which is cheaper, GPT-4 or Qwen3-Coder 480B-A35B Instruct?
Qwen3-Coder 480B-A35B Instruct is cheaper. It lists at $1.50 per million input tokens and $7.50 per million output tokens; GPT-4 lists at $30 and $60.
Is GPT-4 or Qwen3-Coder 480B-A35B Instruct better for coding?
Qwen3-Coder 480B-A35B Instruct scores higher on coding benchmarks: 35.5 versus 31.6 in the Noometry coding category.
Which has the bigger context window?
Qwen3-Coder 480B-A35B Instruct does, with 262K tokens against 8K.
How many benchmarks do GPT-4 and Qwen3-Coder 480B-A35B Instruct share?
18 benchmarks have published results for both models. GPT-4 has 38 scored results on Noometry and Qwen3-Coder 480B-A35B Instruct has 25.