Model comparison
GPT-5.2 Pro vs Llama 3-70B
GPT-5.2 Pro is the stronger model overall, scoring 52.3 to 28.8 on the Noometry Index.
Last verified . 1 shared benchmarks.
MetaSummary
- They share 1 benchmark with published results for both. GPT-5.2 Pro scores higher in 2 categories and Llama 3-70B in 0 categories; 2 gaps are clear of the uncertainty.
- The widest gap is in math, where GPT-5.2 Pro leads 65.3 to 12.8.
- Llama 3-70B has downloadable open weights; the other is API-only.
Side by side
| GPT-5.2 Pro | Llama 3-70B | |
|---|---|---|
| Provider | OpenAI | Meta |
| Noometry Index | 52.3 | 28.8 |
| Released | 2025-12-11 | 2024-04-18 |
| Weights | Proprietary | Open |
| Context window | 400K | — |
| Max output | 128K | — |
| Input $ / M tokens | $21 | — |
| Output $ / M tokens | $168 | — |
| Results tracked | 8 | 31 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
GPT-5.2 Pro: —, Llama 3-70B: 35.8 (#218)
| Benchmark | GPT-5.2 Pro | Llama 3-70B |
|---|---|---|
| BigCodeBench Instruct | — | 43.6% |
| LMArena Coding | — | 1206 |
| BigCodeBench Complete | — | 54.5% |
| HumanEval+ | — | 72% |
| MBPP+ | — | 69% |
Agentic & Tool Use Not comparable
GPT-5.2 Pro: —, Llama 3-70B: 21.1 (#139)
| Benchmark | GPT-5.2 Pro | Llama 3-70B |
|---|---|---|
| Cybench | — | 5% |
Reasoning GPT-5.2 Pro leads
GPT-5.2 Pro: 51.5 (#33), Llama 3-70B: 18.0 (#288)
| Benchmark | GPT-5.2 Pro | Llama 3-70B |
|---|---|---|
| Epoch Capabilities Index | 155.4 | 122.93 |
| ARC-AGI-2 | 54.2% | — |
| SimpleBench | 57.4% | — |
| Kagi LLM Benchmark | — | 35.1% |
| NYT Connections (extended) | 79.3% | — |
| ARC-AGI-1 | 90.5% | — |
| LMArena Hard Prompts | — | 1195 |
| DTBench | — | 54.2% |
| ForecastBench | — | 57.1 |
| WinoGrande | — | 83.5% |
Math GPT-5.2 Pro leads
GPT-5.2 Pro: 65.3 (#29), Llama 3-70B: 12.8 (#305)
| Benchmark | GPT-5.2 Pro | Llama 3-70B |
|---|---|---|
| FrontierMath (Tiers 1-3) | 74% | — |
| FrontierMath Tier 4 | 46% | — |
| OTIS Mock AIME 2024-2025 | — | 4.3% |
| LMArena Math | — | 1218 |
| MATH Level 5 | — | 22.6% |
| FrontierMath Tier 4 (v1) | 31.3% | — |
Knowledge Not comparable
GPT-5.2 Pro: —, Llama 3-70B: 20.8 (#277)
| Benchmark | GPT-5.2 Pro | Llama 3-70B |
|---|---|---|
| GPQA Diamond | — | 40.6% |
| LMArena Expert | — | 1149 |
| MMLU | — | 79.3% |
Multilingual Not comparable
GPT-5.2 Pro: —, Llama 3-70B: 33.6 (#251)
| Benchmark | GPT-5.2 Pro | Llama 3-70B |
|---|---|---|
| LMArena Non-English | — | 1142 |
| LMArena Chinese | — | 1114 |
| LMArena French | — | 1232 |
| LMArena German | — | 1169 |
| LMArena Japanese | — | 1017 |
| LMArena Korean | — | 1017 |
| LMArena Russian | — | 1159 |
| LMArena Spanish | — | 1241 |
Instruction Following Not comparable
GPT-5.2 Pro: —, Llama 3-70B: 62.5 (#238)
| Benchmark | GPT-5.2 Pro | Llama 3-70B |
|---|---|---|
| LMArena Instruction Following | — | 1194 |
Long Context Not comparable
GPT-5.2 Pro: —, Llama 3-70B: 35.6 (#240)
| Benchmark | GPT-5.2 Pro | Llama 3-70B |
|---|---|---|
| LMArena Longer Query | — | 1174 |
Writing & Preference Not comparable
GPT-5.2 Pro: —, Llama 3-70B: 42.8 (#231)
| Benchmark | GPT-5.2 Pro | Llama 3-70B |
|---|---|---|
| LMArena Text | — | 1221 |
| LMArena Creative Writing | — | 1210 |
| LMArena Multi-Turn | — | 1223 |
Frequently asked questions
Is GPT-5.2 Pro better than Llama 3-70B?
GPT-5.2 Pro is the stronger model overall, scoring 52.3 to 28.8 on the Noometry Index.
How many benchmarks do GPT-5.2 Pro and Llama 3-70B share?
1 benchmark has published results for both models. GPT-5.2 Pro has 8 scored results on Noometry and Llama 3-70B has 31.