Model comparison
GPT-5-Codex vs Qwen3 235B-A22B
Qwen3 235B-A22B is the stronger model overall, scoring 43.2 to 37.3 on the Noometry Index.
Last verified . 2 shared benchmarks.
Alibaba (Qwen)Summary
- They share 2 benchmarks with published results for both. GPT-5-Codex scores higher in 1 category and Qwen3 235B-A22B in 2 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where GPT-5-Codex leads 30.0 to 15.8.
- The biggest single-benchmark swing is WeirdML: 54.5% for GPT-5-Codex and 41% for Qwen3 235B-A22B.
- Qwen3 235B-A22B is cheaper at $0.70 / $2.80 per million input/output tokens, against $1.25 / $10 for GPT-5-Codex.
- GPT-5-Codex accepts more context: 400K tokens versus 131K.
- Qwen3 235B-A22B has downloadable open weights; the other is API-only.
Side by side
| GPT-5-Codex | Qwen3 235B-A22B | |
|---|---|---|
| Provider | OpenAI | Alibaba (Qwen) |
| Noometry Index | 37.3 | 43.2 |
| Released | 2025-09-15 | 2025-04 |
| Weights | Proprietary | Open |
| Context window | 400K | 131K |
| Max output | 128K | 16K |
| Input $ / M tokens | $1.25 | $0.70 |
| Output $ / M tokens | $10 | $2.80 |
| Results tracked | 3 | 49 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3 235B-A22B leads
GPT-5-Codex: 41.9 (#100), Qwen3 235B-A22B: 43.8 (#72)
| Benchmark | GPT-5-Codex | Qwen3 235B-A22B |
|---|---|---|
| WeirdML | 54.5% | 41% |
| Aider Polyglot | — | 59.6% |
| SciCode | — | 42.4% |
| LMArena Coding | — | 1445 |
Agentic & Tool Use Qwen3 235B-A22B leads
GPT-5-Codex: 30.8 (#66), Qwen3 235B-A22B: 33.7 (#48)
| Benchmark | GPT-5-Codex | Qwen3 235B-A22B |
|---|---|---|
| Terminal-Bench | 44.3% | — |
| Berkeley Function Calling Leaderboard | — | 52.1% |
| Vending-Bench 2 | — | -11.34 |
Reasoning GPT-5-Codex leads
GPT-5-Codex: 30.0 (#80), Qwen3 235B-A22B: 15.8 (#302)
| Benchmark | GPT-5-Codex | Qwen3 235B-A22B |
|---|---|---|
| Kagi LLM Benchmark | 70.3% | 69.4% |
| ARC-AGI-2 | — | 1.3% |
| SimpleBench | — | 31% |
| ARC-AGI-1 | — | 11% |
| CritPt | — | 0% |
| Chess Puzzles | — | 12% |
| LMArena Hard Prompts | — | 1433 |
| Mystery Game Puzzles | — | 9% |
| DTBench | — | 80.3% |
| LMCA | — | 29.3% |
| Epoch Capabilities Index | — | 143.87 |
| ForecastBench | — | 59.7 |
Math Not comparable
GPT-5-Codex: —, Qwen3 235B-A22B: 48.5 (#51)
| Benchmark | GPT-5-Codex | Qwen3 235B-A22B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 86.7% |
| Omni-MATH | — | 71.8% |
| LMArena Math | — | 1431 |
| MATH Level 5 | — | 68.9% |
| FrontierMath (Feb 2025 set) | — | 8.5% |
| FrontierMath Tier 4 (v1) | — | 0% |
Knowledge Not comparable
GPT-5-Codex: —, Qwen3 235B-A22B: 49.5 (#67)
| Benchmark | GPT-5-Codex | Qwen3 235B-A22B |
|---|---|---|
| GPQA Diamond | — | 80.1% |
| SimpleQA Verified | — | 40.4% |
| MMLU-Pro | — | 84.4% |
| Confabulations | — | 15.6% |
| Vectara Hallucination Rate | — | 9.3% |
| GPQA (HELM) | — | 72.7% |
| LMArena Expert | — | 1460 |
Multilingual Not comparable
GPT-5-Codex: —, Qwen3 235B-A22B: 52.5 (#84)
| Benchmark | GPT-5-Codex | Qwen3 235B-A22B |
|---|---|---|
| LMArena Non-English | — | 1410 |
| LMArena Chinese | — | 1481 |
| LMArena French | — | 1445 |
| LMArena German | — | 1432 |
| LMArena Japanese | — | 1400 |
| LMArena Korean | — | 1391 |
| LMArena Russian | — | 1411 |
| LMArena Spanish | — | 1429 |
Instruction Following Not comparable
GPT-5-Codex: —, Qwen3 235B-A22B: 72.8 (#132)
| Benchmark | GPT-5-Codex | Qwen3 235B-A22B |
|---|---|---|
| IFEval | — | 83.5% |
| LMArena Instruction Following | — | 1408 |
Long Context Not comparable
GPT-5-Codex: —, Qwen3 235B-A22B: 46.1 (#25)
| Benchmark | GPT-5-Codex | Qwen3 235B-A22B |
|---|---|---|
| Fiction.LiveBench | — | 75% |
| LMArena Longer Query | — | 1426 |
Writing & Preference Not comparable
GPT-5-Codex: —, Qwen3 235B-A22B: 59.8 (#103)
| Benchmark | GPT-5-Codex | Qwen3 235B-A22B |
|---|---|---|
| LMArena Text | — | 1419 |
| LMArena Creative Writing | — | 1384 |
| Short-Story Creative Writing | — | 83% |
| EQ-Bench Creative Writing | — | 1366 |
| WildBench | — | 86.6% |
| LMArena Multi-Turn | — | 1432 |
Frequently asked questions
Is GPT-5-Codex better than Qwen3 235B-A22B?
Qwen3 235B-A22B is the stronger model overall, scoring 43.2 to 37.3 on the Noometry Index.
Which is cheaper, GPT-5-Codex or Qwen3 235B-A22B?
Qwen3 235B-A22B is cheaper. It lists at $0.70 per million input tokens and $2.80 per million output tokens; GPT-5-Codex lists at $1.25 and $10.
Is GPT-5-Codex or Qwen3 235B-A22B better for coding?
Qwen3 235B-A22B scores higher on coding benchmarks: 43.8 versus 41.9 in the Noometry coding category.
Which has the bigger context window?
GPT-5-Codex does, with 400K tokens against 131K.
How many benchmarks do GPT-5-Codex and Qwen3 235B-A22B share?
2 benchmarks have published results for both models. GPT-5-Codex has 3 scored results on Noometry and Qwen3 235B-A22B has 49.