Model comparison
GPT-5-Codex vs Hunyuan Turbos 20250226
Hunyuan Turbos 20250226 is the stronger model overall, scoring 41.3 to 37.9 on the Noometry Index.
Last verified . 0 shared benchmarks.
TencentSummary
- The widest gap is in reasoning, where GPT-5-Codex leads 30.9 to 27.8.
Side by side
| GPT-5-Codex | Hunyuan Turbos 20250226 | |
|---|---|---|
| Provider | OpenAI | Tencent |
| Noometry Index | 37.9 | 41.3 |
| Released | 2025-09-15 | — |
| Weights | Proprietary | Proprietary |
| Context window | 400K | — |
| Max output | 128K | — |
| Input $ / M tokens | $1.25 | — |
| Output $ / M tokens | $10 | — |
| Results tracked | 3 | 16 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5-Codex leads
GPT-5-Codex: 42.4 (#103), Hunyuan Turbos 20250226: 40.0 (#152)
| Benchmark | GPT-5-Codex | Hunyuan Turbos 20250226 |
|---|---|---|
| WeirdML | 54.5% | — |
| LMArena Coding | — | 1361 |
Agentic & Tool Use Not comparable
GPT-5-Codex: 31.0 (#72), Hunyuan Turbos 20250226: —
| Benchmark | GPT-5-Codex | Hunyuan Turbos 20250226 |
|---|---|---|
| Terminal-Bench | 44.3% | — |
Reasoning GPT-5-Codex leads
GPT-5-Codex: 30.9 (#83), Hunyuan Turbos 20250226: 27.8 (#113)
| Benchmark | GPT-5-Codex | Hunyuan Turbos 20250226 |
|---|---|---|
| Kagi LLM Benchmark | 70.3% | — |
| LMArena Hard Prompts | — | 1374 |
Math Not comparable
GPT-5-Codex: —, Hunyuan Turbos 20250226: 37.5 (#154)
| Benchmark | GPT-5-Codex | Hunyuan Turbos 20250226 |
|---|---|---|
| LMArena Math | — | 1359 |
Knowledge Not comparable
GPT-5-Codex: —, Hunyuan Turbos 20250226: 37.0 (#161)
| Benchmark | GPT-5-Codex | Hunyuan Turbos 20250226 |
|---|---|---|
| LMArena Expert | — | 1339 |
Multilingual Not comparable
GPT-5-Codex: —, Hunyuan Turbos 20250226: 48.9 (#136)
| Benchmark | GPT-5-Codex | Hunyuan Turbos 20250226 |
|---|---|---|
| LMArena Non-English | — | 1363 |
| LMArena Chinese | — | 1417 |
| LMArena French | — | 1391 |
| LMArena German | — | 1355 |
| LMArena Japanese | — | 1342 |
| LMArena Korean | — | 1351 |
| LMArena Russian | — | 1368 |
Instruction Following Not comparable
GPT-5-Codex: —, Hunyuan Turbos 20250226: 71.0 (#158)
| Benchmark | GPT-5-Codex | Hunyuan Turbos 20250226 |
|---|---|---|
| LMArena Instruction Following | — | 1344 |
Long Context Not comparable
GPT-5-Codex: —, Hunyuan Turbos 20250226: 41.6 (#136)
| Benchmark | GPT-5-Codex | Hunyuan Turbos 20250226 |
|---|---|---|
| LMArena Longer Query | — | 1366 |
Writing & Preference Not comparable
GPT-5-Codex: —, Hunyuan Turbos 20250226: 57.4 (#128)
| Benchmark | GPT-5-Codex | Hunyuan Turbos 20250226 |
|---|---|---|
| LMArena Text | — | 1377 |
| LMArena Creative Writing | — | 1359 |
| LMArena Multi-Turn | — | 1387 |
Frequently asked questions
Is GPT-5-Codex better than Hunyuan Turbos 20250226?
Hunyuan Turbos 20250226 is the stronger model overall, scoring 41.3 to 37.9 on the Noometry Index.
Is GPT-5-Codex or Hunyuan Turbos 20250226 better for coding?
GPT-5-Codex scores higher on coding benchmarks: 42.4 versus 40.0 in the Noometry coding category.
How many benchmarks do GPT-5-Codex and Hunyuan Turbos 20250226 share?
0 benchmarks have published results for both models. GPT-5-Codex has 3 scored results on Noometry and Hunyuan Turbos 20250226 has 16.