Model comparison
GPT-5.2 Codex vs Llama2 70b Steerlm Chat
GPT-5.2 Codex is the stronger model overall, scoring 42.2 to 31.2 on the Noometry Index.
Last verified . 0 shared benchmarks.
NVIDIASummary
- The widest gap is in coding, where GPT-5.2 Codex leads 45.4 to 29.3.
- Llama2 70b Steerlm Chat has downloadable open weights; the other is API-only.
Side by side
| GPT-5.2 Codex | Llama2 70b Steerlm Chat | |
|---|---|---|
| Provider | OpenAI | NVIDIA |
| Noometry Index | 42.2 | 31.2 |
| Released | 2025-12-18 | — |
| Weights | Proprietary | Open |
| Context window | 400K | — |
| Max output | 128K | — |
| Input $ / M tokens | $1.75 | — |
| Output $ / M tokens | $14 | — |
| Results tracked | 5 | 9 |
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), Llama2 70b Steerlm Chat: 29.3 (#295)
| Benchmark | GPT-5.2 Codex | Llama2 70b Steerlm Chat |
|---|---|---|
| SWE-bench Verified (bash only) | 72.8% | — |
| LMArena WebDev | 1339 | — |
| SWE-bench Multilingual | 66.3% | — |
| LMArena Coding | — | 1025 |
| ALE-Bench | 1,300 | — |
Agentic & Tool Use Not comparable
GPT-5.2 Codex: 40.7 (#20), Llama2 70b Steerlm Chat: —
| Benchmark | GPT-5.2 Codex | Llama2 70b Steerlm Chat |
|---|---|---|
| Terminal-Bench | 66.5% | — |
Reasoning Not comparable
GPT-5.2 Codex: —, Llama2 70b Steerlm Chat: 19.1 (#245)
| Benchmark | GPT-5.2 Codex | Llama2 70b Steerlm Chat |
|---|---|---|
| LMArena Hard Prompts | — | 1047 |
Math Not comparable
GPT-5.2 Codex: —, Llama2 70b Steerlm Chat: 28.8 (#223)
| Benchmark | GPT-5.2 Codex | Llama2 70b Steerlm Chat |
|---|---|---|
| LMArena Math | — | 1072 |
Multilingual Not comparable
GPT-5.2 Codex: —, Llama2 70b Steerlm Chat: 28.9 (#265)
| Benchmark | GPT-5.2 Codex | Llama2 70b Steerlm Chat |
|---|---|---|
| LMArena Non-English | — | 1064 |
Instruction Following Not comparable
GPT-5.2 Codex: —, Llama2 70b Steerlm Chat: 54.5 (#274)
| Benchmark | GPT-5.2 Codex | Llama2 70b Steerlm Chat |
|---|---|---|
| LMArena Instruction Following | — | 1061 |
Long Context Not comparable
GPT-5.2 Codex: —, Llama2 70b Steerlm Chat: 30.4 (#283)
| Benchmark | GPT-5.2 Codex | Llama2 70b Steerlm Chat |
|---|---|---|
| LMArena Longer Query | — | 998 |
Writing & Preference Not comparable
GPT-5.2 Codex: —, Llama2 70b Steerlm Chat: 31.8 (#278)
| Benchmark | GPT-5.2 Codex | Llama2 70b Steerlm Chat |
|---|---|---|
| LMArena Text | — | 1098 |
| LMArena Creative Writing | — | 1091 |
| LMArena Multi-Turn | — | 1058 |
Frequently asked questions
Is GPT-5.2 Codex better than Llama2 70b Steerlm Chat?
GPT-5.2 Codex is the stronger model overall, scoring 42.2 to 31.2 on the Noometry Index.
Is GPT-5.2 Codex or Llama2 70b Steerlm Chat better for coding?
GPT-5.2 Codex scores higher on coding benchmarks: 45.4 versus 29.3 in the Noometry coding category.
How many benchmarks do GPT-5.2 Codex and Llama2 70b Steerlm Chat share?
0 benchmarks have published results for both models. GPT-5.2 Codex has 5 scored results on Noometry and Llama2 70b Steerlm Chat has 9.