Model comparison
GPT-5.2 Codex vs Qwen2.5 Plus 1127
GPT-5.2 Codex is the stronger model overall, scoring 42.2 to 38.1 on the Noometry Index.
Last verified . 0 shared benchmarks.
Alibaba (Qwen)Summary
- The widest gap is in coding, where GPT-5.2 Codex leads 45.4 to 37.9.
Side by side
| GPT-5.2 Codex | Qwen2.5 Plus 1127 | |
|---|---|---|
| Provider | OpenAI | Alibaba (Qwen) |
| Noometry Index | 42.2 | 38.1 |
| Released | 2025-12-18 | — |
| Weights | Proprietary | Proprietary |
| Context window | 400K | — |
| Max output | 128K | — |
| Input $ / M tokens | $1.75 | — |
| Output $ / M tokens | $14 | — |
| Results tracked | 5 | 14 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5.2 Codex leads
GPT-5.2 Codex: 45.4 (#66), Qwen2.5 Plus 1127: 37.9 (#171)
| Benchmark | GPT-5.2 Codex | Qwen2.5 Plus 1127 |
|---|---|---|
| SWE-bench Verified (bash only) | 72.8% | — |
| LMArena WebDev | 1339 | — |
| SWE-bench Multilingual | 66.3% | — |
| LMArena Coding | — | 1314 |
| ALE-Bench | 1,300 | — |
Agentic & Tool Use Not comparable
GPT-5.2 Codex: 40.7 (#20), Qwen2.5 Plus 1127: —
| Benchmark | GPT-5.2 Codex | Qwen2.5 Plus 1127 |
|---|---|---|
| Terminal-Bench | 66.5% | — |
Reasoning Not comparable
GPT-5.2 Codex: —, Qwen2.5 Plus 1127: 24.8 (#139)
| Benchmark | GPT-5.2 Codex | Qwen2.5 Plus 1127 |
|---|---|---|
| LMArena Hard Prompts | — | 1299 |
Math Not comparable
GPT-5.2 Codex: —, Qwen2.5 Plus 1127: 33.5 (#175)
| Benchmark | GPT-5.2 Codex | Qwen2.5 Plus 1127 |
|---|---|---|
| LMArena Math | — | 1298 |
Knowledge Not comparable
GPT-5.2 Codex: —, Qwen2.5 Plus 1127: 34.9 (#179)
| Benchmark | GPT-5.2 Codex | Qwen2.5 Plus 1127 |
|---|---|---|
| LMArena Expert | — | 1289 |
Multilingual Not comparable
GPT-5.2 Codex: —, Qwen2.5 Plus 1127: 42.1 (#196)
| Benchmark | GPT-5.2 Codex | Qwen2.5 Plus 1127 |
|---|---|---|
| LMArena Non-English | — | 1265 |
| LMArena Chinese | — | 1314 |
| LMArena German | — | 1231 |
| LMArena Japanese | — | 1207 |
| LMArena Russian | — | 1271 |
Instruction Following Not comparable
GPT-5.2 Codex: —, Qwen2.5 Plus 1127: 67.4 (#194)
| Benchmark | GPT-5.2 Codex | Qwen2.5 Plus 1127 |
|---|---|---|
| LMArena Instruction Following | — | 1275 |
Long Context Not comparable
GPT-5.2 Codex: —, Qwen2.5 Plus 1127: 39.2 (#180)
| Benchmark | GPT-5.2 Codex | Qwen2.5 Plus 1127 |
|---|---|---|
| LMArena Longer Query | — | 1292 |
Writing & Preference Not comparable
GPT-5.2 Codex: —, Qwen2.5 Plus 1127: 49.5 (#186)
| Benchmark | GPT-5.2 Codex | Qwen2.5 Plus 1127 |
|---|---|---|
| LMArena Text | — | 1299 |
| LMArena Creative Writing | — | 1262 |
| LMArena Multi-Turn | — | 1299 |
Frequently asked questions
Is GPT-5.2 Codex better than Qwen2.5 Plus 1127?
GPT-5.2 Codex is the stronger model overall, scoring 42.2 to 38.1 on the Noometry Index.
Is GPT-5.2 Codex or Qwen2.5 Plus 1127 better for coding?
GPT-5.2 Codex scores higher on coding benchmarks: 45.4 versus 37.9 in the Noometry coding category.
How many benchmarks do GPT-5.2 Codex and Qwen2.5 Plus 1127 share?
0 benchmarks have published results for both models. GPT-5.2 Codex has 5 scored results on Noometry and Qwen2.5 Plus 1127 has 14.