Model comparison
GPT-5.2 Codex vs Llama-3.3-70B-Instruct
GPT-5.2 Codex is the stronger model overall, scoring 42.6 to 30.6 on the Noometry Index. Llama-3.3-70B-Instruct costs 31× less per token, which makes it the better buy when GPT-5.2 Codex's lead doesn't matter for your workload.
Last verified . 0 shared benchmarks.
MetaSummary
- The widest gap is in agentic & tool use, where GPT-5.2 Codex leads 41.0 to 25.8.
- Llama-3.3-70B-Instruct is cheaper at $0.10 / $0.32 per million input/output tokens, against $1.75 / $14 for GPT-5.2 Codex.
- GPT-5.2 Codex accepts more context: 400K tokens versus 128K.
- Llama-3.3-70B-Instruct has downloadable open weights; the other is API-only.
Side by side
| GPT-5.2 Codex | Llama-3.3-70B-Instruct | |
|---|---|---|
| Provider | OpenAI | Meta |
| Noometry Index | 42.6 | 30.6 |
| Released | 2025-12-18 | 2024-12-06 |
| Weights | Proprietary | Open |
| Context window | 400K | 128K |
| Max output | 128K | 4K |
| Input $ / M tokens | $1.75 | $0.10 |
| Output $ / M tokens | $14 | $0.32 |
| Results tracked | 5 | 43 |
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), Llama-3.3-70B-Instruct: 31.0 (#290)
| Benchmark | GPT-5.2 Codex | Llama-3.3-70B-Instruct |
|---|---|---|
| SWE-bench Verified (bash only) | 72.8% | — |
| LMArena WebDev | 1339 | — |
| SWE-bench Multilingual | 66.3% | — |
| SciCode | — | 26% |
| WeirdML | — | 14.4% |
| BigCodeBench Instruct | — | 46.9% |
| LiveBench Coding | — | 36.6% |
| LMArena Coding | — | 1268 |
| BigCodeBench Complete | — | 57.5% |
| ALE-Bench | 1,300 | — |
Agentic & Tool Use GPT-5.2 Codex leads
GPT-5.2 Codex: 41.0 (#22), Llama-3.3-70B-Instruct: 25.8 (#105)
| Benchmark | GPT-5.2 Codex | Llama-3.3-70B-Instruct |
|---|---|---|
| Terminal-Bench | 66.5% | — |
| Berkeley Function Calling Leaderboard | — | 31.9% |
| BALROG | — | 23% |
Reasoning Not comparable
GPT-5.2 Codex: —, Llama-3.3-70B-Instruct: 14.1 (#327)
| Benchmark | GPT-5.2 Codex | Llama-3.3-70B-Instruct |
|---|---|---|
| SimpleBench | — | 19.9% |
| CritPt | — | 0% |
| LiveBench Reasoning | — | 50.8% |
| LMArena Hard Prompts | — | 1257 |
| DTBench | — | 59.5% |
| LiveBench Data Analysis | — | 49.5% |
| LMCA | — | 17.5% |
| Epoch Capabilities Index | — | 127.33 |
| ForecastBench | — | 58.6 |
| LiveBench | — | 50.2% |
Math Not comparable
GPT-5.2 Codex: —, Llama-3.3-70B-Instruct: 15.3 (#298)
| Benchmark | GPT-5.2 Codex | Llama-3.3-70B-Instruct |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 5.1% |
| LiveBench Math | — | 42.2% |
| LMArena Math | — | 1267 |
| MATH Level 5 | — | 41.6% |
Knowledge Not comparable
GPT-5.2 Codex: —, Llama-3.3-70B-Instruct: 30.6 (#226)
| Benchmark | GPT-5.2 Codex | Llama-3.3-70B-Instruct |
|---|---|---|
| GPQA Diamond | — | 47.4% |
| Confabulations | — | 22.8% |
| Vectara Hallucination Rate | — | 4.1% |
| LMArena Expert | — | 1225 |
| MMLU | — | 86.3% |
Multilingual Not comparable
GPT-5.2 Codex: —, Llama-3.3-70B-Instruct: 39.9 (#220)
| Benchmark | GPT-5.2 Codex | Llama-3.3-70B-Instruct |
|---|---|---|
| LMArena Non-English | — | 1236 |
| LMArena Chinese | — | 1217 |
| LMArena French | — | 1281 |
| LMArena German | — | 1251 |
| LMArena Japanese | — | 1150 |
| LMArena Korean | — | 1143 |
| LMArena Russian | — | 1252 |
| LMArena Spanish | — | 1270 |
Instruction Following Not comparable
GPT-5.2 Codex: —, Llama-3.3-70B-Instruct: 71.1 (#157)
| Benchmark | GPT-5.2 Codex | Llama-3.3-70B-Instruct |
|---|---|---|
| LiveBench Instruction Following | — | 82.7% |
| LMArena Instruction Following | — | 1242 |
Long Context Not comparable
GPT-5.2 Codex: —, Llama-3.3-70B-Instruct: 26.4 (#295)
| Benchmark | GPT-5.2 Codex | Llama-3.3-70B-Instruct |
|---|---|---|
| Fiction.LiveBench | — | 33.3% |
| LMArena Longer Query | — | 1256 |
Writing & Preference Not comparable
GPT-5.2 Codex: —, Llama-3.3-70B-Instruct: 47.6 (#207)
| Benchmark | GPT-5.2 Codex | Llama-3.3-70B-Instruct |
|---|---|---|
| LMArena Text | — | 1274 |
| LMArena Creative Writing | — | 1250 |
| LMArena Multi-Turn | — | 1280 |
| LiveBench Language | — | 39.2% |
Frequently asked questions
Is GPT-5.2 Codex better than Llama-3.3-70B-Instruct?
GPT-5.2 Codex is the stronger model overall, scoring 42.6 to 30.6 on the Noometry Index. Llama-3.3-70B-Instruct costs 31× less per token, which makes it the better buy when GPT-5.2 Codex's lead doesn't matter for your workload.
Which is cheaper, GPT-5.2 Codex or Llama-3.3-70B-Instruct?
Llama-3.3-70B-Instruct is cheaper. It lists at $0.10 per million input tokens and $0.32 per million output tokens; GPT-5.2 Codex lists at $1.75 and $14.
Is GPT-5.2 Codex or Llama-3.3-70B-Instruct better for coding?
GPT-5.2 Codex scores higher on coding benchmarks: 45.5 versus 31.0 in the Noometry coding category.
Which has the bigger context window?
GPT-5.2 Codex does, with 400K tokens against 128K.
How many benchmarks do GPT-5.2 Codex and Llama-3.3-70B-Instruct share?
0 benchmarks have published results for both models. GPT-5.2 Codex has 5 scored results on Noometry and Llama-3.3-70B-Instruct has 43.