Model comparison
GPT-4.5 vs Llama 3.1-70B
GPT-4.5 is the stronger model overall, scoring 36.9 to 29.4 on the Noometry Index.
Last verified . 22 shared benchmarks.
MetaSummary
- They share 22 benchmarks with published results for both. GPT-4.5 scores higher in 8 categories and Llama 3.1-70B in 1 category; 9 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where GPT-4.5 leads 57.1 to 35.6.
- The biggest single-benchmark swing is MATH Level 5: 78.6% for GPT-4.5 and 36.7% for Llama 3.1-70B.
- Llama 3.1-70B has downloadable open weights; the other is API-only.
Side by side
| GPT-4.5 | Llama 3.1-70B | |
|---|---|---|
| Provider | OpenAI | Meta |
| Noometry Index | 36.9 | 29.4 |
| Released | 2025-02-27 | 2024-07-23 |
| Weights | Proprietary | Open |
| Context window | — | 128K |
| Max output | — | 4K |
| Input $ / M tokens | — | $0.40 |
| Output $ / M tokens | — | $0.40 |
| Results tracked | 42 | 35 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-4.5 leads
GPT-4.5: 41.8 (#102), Llama 3.1-70B: 29.8 (#292)
| Benchmark | GPT-4.5 | Llama 3.1-70B |
|---|---|---|
| WeirdML | 39.4% | 9% |
| LMArena Coding | 1397 | 1260 |
| Aider Polyglot | 44.9% | — |
| BigCodeBench Instruct | — | 46.1% |
| LiveBench Coding | 75.2% | — |
| BigCodeBench Complete | — | 54.8% |
Agentic & Tool Use GPT-4.5 leads
GPT-4.5: 27.6 (#92), Llama 3.1-70B: 24.9 (#104)
| Benchmark | GPT-4.5 | Llama 3.1-70B |
|---|---|---|
| TheAgentCompany | — | 6.9% |
| Cybench | 17.5% | — |
| BALROG | — | 27.9% |
Reasoning Llama 3.1-70B leads
GPT-4.5: 14.1 (#320), Llama 3.1-70B: 20.8 (#215)
| Benchmark | GPT-4.5 | Llama 3.1-70B |
|---|---|---|
| LMArena Hard Prompts | 1404 | 1241 |
| Epoch Capabilities Index | 136.74 | 125.91 |
| ARC-AGI-2 | 0.8% | — |
| SimpleBench | 34.5% | — |
| ARC-AGI-1 | 10.3% | — |
| EnigmaEval | 3.2% | — |
| LiveBench Reasoning | 71.1% | — |
| DTBench | — | 60% |
| LiveBench Data Analysis | 64.3% | — |
| LMCA | — | 14.8% |
| ForecastBench | 61.7 | — |
| LiveBench | 69% | — |
Math GPT-4.5 leads
GPT-4.5: 31.0 (#200), Llama 3.1-70B: 12.7 (#298)
| Benchmark | GPT-4.5 | Llama 3.1-70B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 37.8% | 3.6% |
| LMArena Math | 1412 | 1252 |
| MATH Level 5 | 78.6% | 36.7% |
| Omni-MATH | — | 21% |
| LiveBench Math | 69.3% | — |
Knowledge GPT-4.5 leads
GPT-4.5: 32.4 (#205), Llama 3.1-70B: 24.1 (#264)
| Benchmark | GPT-4.5 | Llama 3.1-70B |
|---|---|---|
| GPQA Diamond | 68.7% | 44.2% |
| LMArena Expert | 1394 | 1209 |
| Humanity's Last Exam | 5.4% | — |
| MMLU-Pro | — | 65.3% |
| Confabulations | 13.6% | — |
| GPQA (HELM) | — | 42.6% |
| MMLU | — | 80.1% |
Multimodal Not comparable
GPT-4.5: 37.0 (#68), Llama 3.1-70B: —
| Benchmark | GPT-4.5 | Llama 3.1-70B |
|---|---|---|
| LMArena Vision | 1195 | — |
| VPCT | 45% | — |
Multilingual GPT-4.5 leads
GPT-4.5: 52.7 (#78), Llama 3.1-70B: 38.9 (#220)
| Benchmark | GPT-4.5 | Llama 3.1-70B |
|---|---|---|
| LMArena Non-English | 1413 | 1219 |
| LMArena Chinese | 1421 | 1215 |
| LMArena French | 1417 | 1260 |
| LMArena German | 1457 | 1222 |
| LMArena Japanese | 1416 | 1132 |
| LMArena Korean | 1392 | 1140 |
| LMArena Russian | 1419 | 1234 |
| LMArena Spanish | — | 1253 |
Instruction Following GPT-4.5 leads
GPT-4.5: 72.8 (#129), Llama 3.1-70B: 65.5 (#218)
| Benchmark | GPT-4.5 | Llama 3.1-70B |
|---|---|---|
| LMArena Instruction Following | 1404 | 1231 |
| LiveBench Instruction Following | 72.3% | — |
| IFEval | — | 82.1% |
Long Context GPT-4.5 leads
GPT-4.5: 40.4 (#150), Llama 3.1-70B: 37.6 (#208)
| Benchmark | GPT-4.5 | Llama 3.1-70B |
|---|---|---|
| LMArena Longer Query | 1406 | 1241 |
| Fiction.LiveBench | 63.9% | — |
Writing & Preference GPT-4.5 leads
GPT-4.5: 57.1 (#129), Llama 3.1-70B: 35.6 (#262)
| Benchmark | GPT-4.5 | Llama 3.1-70B |
|---|---|---|
| LMArena Text | 1417 | 1261 |
| LMArena Creative Writing | 1394 | 1232 |
| EQ-Bench Creative Writing | 1258 | 784 |
| LMArena Multi-Turn | 1444 | 1256 |
| Short-Story Creative Writing | 75.6% | — |
| WildBench | — | 75.8% |
| LiveBench Language | 61.5% | — |
Frequently asked questions
Is GPT-4.5 better than Llama 3.1-70B?
GPT-4.5 is the stronger model overall, scoring 36.9 to 29.4 on the Noometry Index.
Is GPT-4.5 or Llama 3.1-70B better for coding?
GPT-4.5 scores higher on coding benchmarks: 41.8 versus 29.8 in the Noometry coding category.
How many benchmarks do GPT-4.5 and Llama 3.1-70B share?
22 benchmarks have published results for both models. GPT-4.5 has 42 scored results on Noometry and Llama 3.1-70B has 35.