Model comparison
GPT-5.2 Codex vs Qwen3.8 27B
Qwen3.8 27B is the stronger model overall, scoring 46.0 to 42.6 on the Noometry Index.
Last verified . 1 shared benchmarks.
Alibaba (Qwen)Summary
- They share 1 benchmark with published results for both. GPT-5.2 Codex scores higher in 1 category and Qwen3.8 27B in 1 category; 2 gaps are clear of the uncertainty.
- The widest gap is in agentic & tool use, where GPT-5.2 Codex leads 41.0 to 32.9.
- Qwen3.8 27B is cheaper at $0.99 / $1.49 per million input/output tokens, against $1.75 / $14 for GPT-5.2 Codex.
- GPT-5.2 Codex accepts more context: 400K tokens versus 262K.
- Qwen3.8 27B has downloadable open weights; the other is API-only.
Side by side
| GPT-5.2 Codex | Qwen3.8 27B | |
|---|---|---|
| Provider | OpenAI | Alibaba (Qwen) |
| Noometry Index | 42.6 | 46.0 |
| Released | 2025-12-18 | 2026-08-14 |
| Weights | Proprietary | Open |
| Context window | 400K | 262K |
| Max output | 128K | 33K |
| Input $ / M tokens | $1.75 | $0.99 |
| Output $ / M tokens | $14 | $1.49 |
| Results tracked | 5 | 31 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3.8 27B leads
GPT-5.2 Codex: 45.5 (#71), Qwen3.8 27B: 50.5 (#44)
| Benchmark | GPT-5.2 Codex | Qwen3.8 27B |
|---|---|---|
| LMArena WebDev | 1339 | 1593 |
| SWE-bench Verified (bash only) | 72.8% | — |
| SWE-bench Multilingual | 66.3% | — |
| SciCode | — | 46.6% |
| LMArena Coding | — | 1482 |
| ALE-Bench | 1,300 | — |
Agentic & Tool Use GPT-5.2 Codex leads
GPT-5.2 Codex: 41.0 (#22), Qwen3.8 27B: 32.9 (#57)
| Benchmark | GPT-5.2 Codex | Qwen3.8 27B |
|---|---|---|
| Terminal-Bench | 66.5% | — |
| APEX-Agents | — | 47.5% |
Reasoning Not comparable
GPT-5.2 Codex: —, Qwen3.8 27B: 41.0 (#54)
| Benchmark | GPT-5.2 Codex | Qwen3.8 27B |
|---|---|---|
| ARC-AGI-2 | — | 42.4% |
| NYT Connections (extended) | — | 54.5% |
| ARC-AGI-1 | — | 87.5% |
| CritPt | — | 5.4% |
| LMArena Hard Prompts | — | 1460 |
| DTBench | — | 88% |
| LMCA | — | 41.4% |
| Surface Evolver Bench | — | 45% |
| Epoch Capabilities Index | — | 149.38 |
Math Not comparable
GPT-5.2 Codex: —, Qwen3.8 27B: 37.1 (#161)
| Benchmark | GPT-5.2 Codex | Qwen3.8 27B |
|---|---|---|
| ProofBench | — | 16% |
| LMArena Math | — | 1456 |
Knowledge Not comparable
GPT-5.2 Codex: —, Qwen3.8 27B: 41.6 (#109)
| Benchmark | GPT-5.2 Codex | Qwen3.8 27B |
|---|---|---|
| LMArena Expert | — | 1482 |
Multimodal Not comparable
GPT-5.2 Codex: —, Qwen3.8 27B: 41.3 (#37)
| Benchmark | GPT-5.2 Codex | Qwen3.8 27B |
|---|---|---|
| LMArena Vision | — | 1271 |
Multilingual Not comparable
GPT-5.2 Codex: —, Qwen3.8 27B: 53.7 (#60)
| Benchmark | GPT-5.2 Codex | Qwen3.8 27B |
|---|---|---|
| LMArena Non-English | — | 1430 |
| LMArena Chinese | — | 1504 |
| LMArena French | — | 1465 |
| LMArena German | — | 1438 |
| LMArena Japanese | — | 1384 |
| LMArena Korean | — | 1393 |
| LMArena Russian | — | 1415 |
| LMArena Spanish | — | 1448 |
Instruction Following Not comparable
GPT-5.2 Codex: —, Qwen3.8 27B: 75.8 (#53)
| Benchmark | GPT-5.2 Codex | Qwen3.8 27B |
|---|---|---|
| LMArena Instruction Following | — | 1439 |
Long Context Not comparable
GPT-5.2 Codex: —, Qwen3.8 27B: 44.3 (#70)
| Benchmark | GPT-5.2 Codex | Qwen3.8 27B |
|---|---|---|
| LMArena Longer Query | — | 1450 |
Writing & Preference Not comparable
GPT-5.2 Codex: —, Qwen3.8 27B: 65.8 (#43)
| Benchmark | GPT-5.2 Codex | Qwen3.8 27B |
|---|---|---|
| LMArena Text | — | 1441 |
| LMArena Creative Writing | — | 1384 |
| EQ-Bench Creative Writing | — | 1671 |
| LMArena Multi-Turn | — | 1441 |
Frequently asked questions
Is GPT-5.2 Codex better than Qwen3.8 27B?
Qwen3.8 27B is the stronger model overall, scoring 46.0 to 42.6 on the Noometry Index.
Which is cheaper, GPT-5.2 Codex or Qwen3.8 27B?
Qwen3.8 27B is cheaper. It lists at $0.99 per million input tokens and $1.49 per million output tokens; GPT-5.2 Codex lists at $1.75 and $14.
Is GPT-5.2 Codex or Qwen3.8 27B better for coding?
Qwen3.8 27B scores higher on coding benchmarks: 50.5 versus 45.5 in the Noometry coding category.
Which has the bigger context window?
GPT-5.2 Codex does, with 400K tokens against 262K.
How many benchmarks do GPT-5.2 Codex and Qwen3.8 27B share?
1 benchmark has published results for both models. GPT-5.2 Codex has 5 scored results on Noometry and Qwen3.8 27B has 31.