Model comparison
GPT-5-Codex vs Qwen3-30B-A3B
Qwen3-30B-A3B is the stronger model overall, scoring 38.5 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 3 categories and Qwen3-30B-A3B in 0 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where GPT-5-Codex leads 30.0 to 21.6.
- The biggest single-benchmark swing is WeirdML: 54.5% for GPT-5-Codex and 29.8% for Qwen3-30B-A3B.
- Qwen3-30B-A3B is cheaper at $0.12 / $0.50 per million input/output tokens, against $1.25 / $10 for GPT-5-Codex.
- GPT-5-Codex accepts more context: 400K tokens versus 41K.
- Qwen3-30B-A3B has downloadable open weights; the other is API-only.
Side by side
| GPT-5-Codex | Qwen3-30B-A3B | |
|---|---|---|
| Provider | OpenAI | Alibaba (Qwen) |
| Noometry Index | 37.3 | 38.5 |
| Released | 2025-09-15 | 2025-04-28 |
| Weights | Proprietary | Open |
| Context window | 400K | 41K |
| Max output | 128K | 16K |
| Input $ / M tokens | $1.25 | $0.12 |
| Output $ / M tokens | $10 | $0.50 |
| Results tracked | 3 | 32 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5-Codex leads
GPT-5-Codex: 41.9 (#100), Qwen3-30B-A3B: 37.0 (#188)
| Benchmark | GPT-5-Codex | Qwen3-30B-A3B |
|---|---|---|
| WeirdML | 54.5% | 29.8% |
| SciCode | — | 33.3% |
| LMArena Coding | — | 1416 |
Agentic & Tool Use GPT-5-Codex leads
GPT-5-Codex: 30.8 (#66), Qwen3-30B-A3B: 29.5 (#75)
| Benchmark | GPT-5-Codex | Qwen3-30B-A3B |
|---|---|---|
| Terminal-Bench | 44.3% | — |
| Berkeley Function Calling Leaderboard | — | 41.4% |
Reasoning GPT-5-Codex leads
GPT-5-Codex: 30.0 (#80), Qwen3-30B-A3B: 21.6 (#193)
| Benchmark | GPT-5-Codex | Qwen3-30B-A3B |
|---|---|---|
| Kagi LLM Benchmark | 70.3% | 54.9% |
| CritPt | — | 0.3% |
| Chess Puzzles | — | 8% |
| LMArena Hard Prompts | — | 1398 |
| DTBench | — | 69.3% |
| LMCA | — | 22.4% |
| Epoch Capabilities Index | — | 139.63 |
Math Not comparable
GPT-5-Codex: —, Qwen3-30B-A3B: 36.0 (#133)
| Benchmark | GPT-5-Codex | Qwen3-30B-A3B |
|---|---|---|
| MathArena Final-Answer Competitions | — | 47.8% |
| OTIS Mock AIME 2024-2025 | — | 70.3% |
| LMArena Math | — | 1394 |
Knowledge Not comparable
GPT-5-Codex: —, Qwen3-30B-A3B: 41.7 (#96)
| Benchmark | GPT-5-Codex | Qwen3-30B-A3B |
|---|---|---|
| GPQA Diamond | — | 70.1% |
| Confabulations | — | 12.3% |
| LMArena Expert | — | 1395 |
Multilingual Not comparable
GPT-5-Codex: —, Qwen3-30B-A3B: 49.8 (#126)
| Benchmark | GPT-5-Codex | Qwen3-30B-A3B |
|---|---|---|
| LMArena Non-English | — | 1372 |
| LMArena Chinese | — | 1434 |
| LMArena French | — | 1419 |
| LMArena German | — | 1379 |
| LMArena Japanese | — | 1338 |
| LMArena Korean | — | 1333 |
| LMArena Russian | — | 1369 |
| LMArena Spanish | — | 1403 |
Instruction Following Not comparable
GPT-5-Codex: —, Qwen3-30B-A3B: 72.2 (#137)
| Benchmark | GPT-5-Codex | Qwen3-30B-A3B |
|---|---|---|
| LMArena Instruction Following | — | 1364 |
Long Context Not comparable
GPT-5-Codex: —, Qwen3-30B-A3B: 31.0 (#278)
| Benchmark | GPT-5-Codex | Qwen3-30B-A3B |
|---|---|---|
| Fiction.LiveBench | — | 40.6% |
| LMArena Longer Query | — | 1379 |
Writing & Preference Not comparable
GPT-5-Codex: —, Qwen3-30B-A3B: 55.9 (#138)
| Benchmark | GPT-5-Codex | Qwen3-30B-A3B |
|---|---|---|
| LMArena Text | — | 1384 |
| LMArena Creative Writing | — | 1318 |
| Short-Story Creative Writing | — | 75.3% |
| LMArena Multi-Turn | — | 1378 |
Frequently asked questions
Is GPT-5-Codex better than Qwen3-30B-A3B?
Qwen3-30B-A3B is the stronger model overall, scoring 38.5 to 37.3 on the Noometry Index.
Which is cheaper, GPT-5-Codex or Qwen3-30B-A3B?
Qwen3-30B-A3B is cheaper. It lists at $0.12 per million input tokens and $0.50 per million output tokens; GPT-5-Codex lists at $1.25 and $10.
Is GPT-5-Codex or Qwen3-30B-A3B better for coding?
GPT-5-Codex scores higher on coding benchmarks: 41.9 versus 37.0 in the Noometry coding category.
Which has the bigger context window?
GPT-5-Codex does, with 400K tokens against 41K.
How many benchmarks do GPT-5-Codex and Qwen3-30B-A3B share?
2 benchmarks have published results for both models. GPT-5-Codex has 3 scored results on Noometry and Qwen3-30B-A3B has 32.