Model comparison
GPT-5.2 Codex vs Qwen-14B
GPT-5.2 Codex is the stronger model overall, scoring 42.6 to 31.4 on the Noometry Index.
Last verified . 0 shared benchmarks.
Alibaba (Qwen)Summary
- The widest gap is in coding, where GPT-5.2 Codex leads 45.5 to 31.2.
- Qwen-14B has downloadable open weights; the other is API-only.
Side by side
| GPT-5.2 Codex | Qwen-14B | |
|---|---|---|
| Provider | OpenAI | Alibaba (Qwen) |
| Noometry Index | 42.6 | 31.4 |
| Released | 2025-12-18 | 2023-09-24 |
| Weights | Proprietary | Open |
| Context window | 400K | — |
| Max output | 128K | — |
| Input $ / M tokens | $1.75 | — |
| Output $ / M tokens | $14 | — |
| Results tracked | 5 | 18 |
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: 45.5 (#71), Qwen-14B: 31.2 (#288)
| Benchmark | GPT-5.2 Codex | Qwen-14B |
|---|---|---|
| SWE-bench Verified (bash only) | 72.8% | — |
| LMArena WebDev | 1339 | — |
| SWE-bench Multilingual | 66.3% | — |
| LMArena Coding | — | 1071 |
| ALE-Bench | 1,300 | — |
Agentic & Tool Use Not comparable
GPT-5.2 Codex: 41.0 (#22), Qwen-14B: —
| Benchmark | GPT-5.2 Codex | Qwen-14B |
|---|---|---|
| Terminal-Bench | 66.5% | — |
Reasoning Not comparable
GPT-5.2 Codex: —, Qwen-14B: 19.6 (#257)
| Benchmark | GPT-5.2 Codex | Qwen-14B |
|---|---|---|
| LMArena Hard Prompts | — | 1027 |
| BIG-Bench Hard | — | 55% |
| Epoch Capabilities Index | — | 113.03 |
| LAMBADA | — | 71.1% |
| PIQA | — | 79.9% |
Math Not comparable
GPT-5.2 Codex: —, Qwen-14B: 31.2 (#227)
| Benchmark | GPT-5.2 Codex | Qwen-14B |
|---|---|---|
| LMArena Math | — | 1068 |
| GSM8K | — | 61.3% |
Knowledge Not comparable
GPT-5.2 Codex: —, Qwen-14B: —
| Benchmark | GPT-5.2 Codex | Qwen-14B |
|---|---|---|
| ARC (AI2) Challenge | — | 84.4% |
| BoolQ | — | 86.2% |
| MMLU | — | 66.3% |
Multilingual Not comparable
GPT-5.2 Codex: —, Qwen-14B: 27.5 (#275)
| Benchmark | GPT-5.2 Codex | Qwen-14B |
|---|---|---|
| LMArena Non-English | — | 1041 |
| LMArena Chinese | — | 1077 |
Instruction Following Not comparable
GPT-5.2 Codex: —, Qwen-14B: 52.4 (#289)
| Benchmark | GPT-5.2 Codex | Qwen-14B |
|---|---|---|
| LMArena Instruction Following | — | 1031 |
Long Context Not comparable
GPT-5.2 Codex: —, Qwen-14B: 31.3 (#280)
| Benchmark | GPT-5.2 Codex | Qwen-14B |
|---|---|---|
| LMArena Longer Query | — | 1028 |
Writing & Preference Not comparable
GPT-5.2 Codex: —, Qwen-14B: 27.6 (#299)
| Benchmark | GPT-5.2 Codex | Qwen-14B |
|---|---|---|
| LMArena Text | — | 1051 |
| LMArena Creative Writing | — | 1028 |
| LMArena Multi-Turn | — | 1022 |
Frequently asked questions
Is GPT-5.2 Codex better than Qwen-14B?
GPT-5.2 Codex is the stronger model overall, scoring 42.6 to 31.4 on the Noometry Index.
Is GPT-5.2 Codex or Qwen-14B better for coding?
GPT-5.2 Codex scores higher on coding benchmarks: 45.5 versus 31.2 in the Noometry coding category.
How many benchmarks do GPT-5.2 Codex and Qwen-14B share?
0 benchmarks have published results for both models. GPT-5.2 Codex has 5 scored results on Noometry and Qwen-14B has 18.