Model comparison
GPT-5.1-Codex vs Qwen3 14B
GPT-5.1-Codex is the stronger model overall, scoring 38.6 to 35.5 on the Noometry Index. Qwen3 14B costs 5.6× less per token, which makes it the better buy when GPT-5.1-Codex's lead doesn't matter for your workload.
Last verified . 0 shared benchmarks.
Alibaba (Qwen)Summary
- The widest gap is in agentic & tool use, where GPT-5.1-Codex leads 38.0 to 29.6.
- Qwen3 14B is cheaper at $0.35 / $1.40 per million input/output tokens, against $1.25 / $10 for GPT-5.1-Codex.
- GPT-5.1-Codex accepts more context: 400K tokens versus 131K.
- Qwen3 14B has downloadable open weights; the other is API-only.
Side by side
| GPT-5.1-Codex | Qwen3 14B | |
|---|---|---|
| Provider | OpenAI | Alibaba (Qwen) |
| Noometry Index | 38.6 | 35.5 |
| Released | 2025-11-12 | 2025-04 |
| Weights | Proprietary | Open |
| Context window | 400K | 131K |
| Max output | 128K | 8K |
| Input $ / M tokens | $1.25 | $0.35 |
| Output $ / M tokens | $10 | $1.40 |
| Results tracked | 6 | 12 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5.1-Codex leads
GPT-5.1-Codex: 41.9 (#116), Qwen3 14B: 37.3 (#195)
| Benchmark | GPT-5.1-Codex | Qwen3 14B |
|---|---|---|
| SWE-bench Verified (bash only) | 66% | — |
| LMArena WebDev | 1337 | — |
| SciCode | — | 31.6% |
| ALE-Bench | 1,245 | — |
Agentic & Tool Use GPT-5.1-Codex leads
GPT-5.1-Codex: 38.0 (#33), Qwen3 14B: 29.6 (#83)
| Benchmark | GPT-5.1-Codex | Qwen3 14B |
|---|---|---|
| Terminal-Bench | 60.4% | — |
| Berkeley Function Calling Leaderboard | — | 41% |
| METR Time Horizons | 70.8% | — |
Reasoning Not comparable
GPT-5.1-Codex: —, Qwen3 14B: 18.5 (#280)
| Benchmark | GPT-5.1-Codex | Qwen3 14B |
|---|---|---|
| Kagi LLM Benchmark | — | 49.1% |
| CritPt | — | 0% |
| Chess Puzzles | — | 4% |
| DTBench | — | 64% |
| LMCA | — | 18.2% |
| Epoch Capabilities Index | — | 138.23 |
Math Qwen3 14B leads
GPT-5.1-Codex: 30.3 (#235), Qwen3 14B: 38.6 (#133)
| Benchmark | GPT-5.1-Codex | Qwen3 14B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 66.4% |
| ProofBench | 9% | — |
Knowledge Not comparable
GPT-5.1-Codex: —, Qwen3 14B: 39.3 (#134)
| Benchmark | GPT-5.1-Codex | Qwen3 14B |
|---|---|---|
| GPQA Diamond | — | 63.8% |
| Vectara Hallucination Rate | — | 5.4% |
Long Context Not comparable
GPT-5.1-Codex: —, Qwen3 14B: 38.1 (#204)
| Benchmark | GPT-5.1-Codex | Qwen3 14B |
|---|---|---|
| Fiction.LiveBench | — | 62.5% |
Frequently asked questions
Is GPT-5.1-Codex better than Qwen3 14B?
GPT-5.1-Codex is the stronger model overall, scoring 38.6 to 35.5 on the Noometry Index. Qwen3 14B costs 5.6× less per token, which makes it the better buy when GPT-5.1-Codex's lead doesn't matter for your workload.
Which is cheaper, GPT-5.1-Codex or Qwen3 14B?
Qwen3 14B is cheaper. It lists at $0.35 per million input tokens and $1.40 per million output tokens; GPT-5.1-Codex lists at $1.25 and $10.
Is GPT-5.1-Codex or Qwen3 14B better for coding?
GPT-5.1-Codex scores higher on coding benchmarks: 41.9 versus 37.3 in the Noometry coding category.
Which has the bigger context window?
GPT-5.1-Codex does, with 400K tokens against 131K.
How many benchmarks do GPT-5.1-Codex and Qwen3 14B share?
0 benchmarks have published results for both models. GPT-5.1-Codex has 6 scored results on Noometry and Qwen3 14B has 12.