Model comparison
GPT-6.1 Sol vs Llama 3.1-70B
GPT-6.1 Sol is the stronger model overall, scoring 65.6 to 29.6 on the Noometry Index. Llama 3.1-70B costs 10× less per token, which makes it the better buy when GPT-6.1 Sol's lead doesn't matter for your workload.
Last verified . 15 shared benchmarks.
MetaSummary
- They share 15 benchmarks with published results for both. GPT-6.1 Sol scores higher in 9 categories and Llama 3.1-70B in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where GPT-6.1 Sol leads 93.7 to 13.5.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 100% for GPT-6.1 Sol and 3.6% for Llama 3.1-70B.
- Llama 3.1-70B is cheaper at $0.40 / $0.40 per million input/output tokens, against $2 / $10 for GPT-6.1 Sol.
- GPT-6.1 Sol accepts more context: 1.05M tokens versus 128K.
- Llama 3.1-70B has downloadable open weights; the other is API-only.
Side by side
| GPT-6.1 Sol | Llama 3.1-70B | |
|---|---|---|
| Provider | OpenAI | Meta |
| Noometry Index | 65.6 | 29.6 |
| Released | 2026-09-29 | 2024-07-23 |
| Weights | Proprietary | Open |
| Context window | 1.05M | 128K |
| Max output | 128K | 4K |
| Input $ / M tokens | $2 | $0.40 |
| Output $ / M tokens | $10 | $0.40 |
| Results tracked | 34 | 35 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-6.1 Sol leads
GPT-6.1 Sol: 63.2 (#8), Llama 3.1-70B: 30.3 (#296)
| Benchmark | GPT-6.1 Sol | Llama 3.1-70B |
|---|---|---|
| LMArena Coding | 1487 | 1260 |
| DeepSWE | 75.2% | — |
| FrontierCode | 50.2% | — |
| LMArena WebDev | 1755 | — |
| SciCode | 55.8% | — |
| WeirdML | — | 9% |
| BigCodeBench Instruct | — | 46.1% |
| BigCodeBench Complete | — | 54.8% |
Agentic & Tool Use GPT-6.1 Sol leads
GPT-6.1 Sol: 39.6 (#26), Llama 3.1-70B: 25.1 (#112)
| Benchmark | GPT-6.1 Sol | Llama 3.1-70B |
|---|---|---|
| APEX-Agents | 60% | — |
| TheAgentCompany | — | 6.9% |
| BALROG | — | 27.9% |
| GDP.pdf | 32% | — |
Reasoning GPT-6.1 Sol leads
GPT-6.1 Sol: 81.9 (#2), Llama 3.1-70B: 21.6 (#220)
| Benchmark | GPT-6.1 Sol | Llama 3.1-70B |
|---|---|---|
| LMArena Hard Prompts | 1466 | 1241 |
| Epoch Capabilities Index | 166.09 | 125.92 |
| ARC-AGI-2 | 94.2% | — |
| NYT Connections (extended) | 95.5% | — |
| ARC-AGI-1 | 98.5% | — |
| CritPt | 31.7% | — |
| Chess Puzzles | 61% | — |
| EBR-Bench | 54.3% | — |
| Mystery Game Puzzles | 80% | — |
| DTBench | — | 60% |
| LMCA | — | 14.8% |
Math GPT-6.1 Sol leads
GPT-6.1 Sol: 93.7 (#1), Llama 3.1-70B: 13.5 (#304)
| Benchmark | GPT-6.1 Sol | Llama 3.1-70B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 100% | 3.6% |
| LMArena Math | 1464 | 1252 |
| FrontierMath (Tiers 1-3) | 93.7% | — |
| FrontierMath Tier 4 | 100% | — |
| ProofBench | 99% | — |
| Omni-MATH | — | 21% |
| MATH Level 5 | — | 36.7% |
Knowledge GPT-6.1 Sol leads
GPT-6.1 Sol: 71.8 (#4), Llama 3.1-70B: 24.2 (#269)
| Benchmark | GPT-6.1 Sol | Llama 3.1-70B |
|---|---|---|
| GPQA Diamond | 95.4% | 44.2% |
| LMArena Expert | 1502 | 1209 |
| SimpleQA Verified | 73.9% | — |
| MMLU-Pro | — | 65.3% |
| GPQA (HELM) | — | 42.6% |
| MMLU | — | 80.1% |
Multimodal Not comparable
GPT-6.1 Sol: 52.7 (#5), Llama 3.1-70B: —
| Benchmark | GPT-6.1 Sol | Llama 3.1-70B |
|---|---|---|
| LMArena Vision | 1288 | — |
| Furniture Assembly | 80% | — |
Multilingual GPT-6.1 Sol leads
GPT-6.1 Sol: 54.3 (#46), Llama 3.1-70B: 38.8 (#225)
| Benchmark | GPT-6.1 Sol | Llama 3.1-70B |
|---|---|---|
| LMArena Non-English | 1438 | 1219 |
| LMArena Chinese | 1477 | 1215 |
| LMArena Russian | 1455 | 1234 |
| LMArena French | — | 1261 |
| LMArena German | — | 1222 |
| LMArena Japanese | — | 1132 |
| LMArena Korean | — | 1140 |
| LMArena Spanish | — | 1253 |
Instruction Following GPT-6.1 Sol leads
GPT-6.1 Sol: 77.0 (#29), Llama 3.1-70B: 65.3 (#223)
| Benchmark | GPT-6.1 Sol | Llama 3.1-70B |
|---|---|---|
| LMArena Instruction Following | 1468 | 1231 |
| IFEval | — | 82.1% |
Long Context GPT-6.1 Sol leads
GPT-6.1 Sol: 44.9 (#54), Llama 3.1-70B: 37.6 (#214)
| Benchmark | GPT-6.1 Sol | Llama 3.1-70B |
|---|---|---|
| LMArena Longer Query | 1465 | 1241 |
Writing & Preference GPT-6.1 Sol leads
GPT-6.1 Sol: 63.6 (#63), Llama 3.1-70B: 35.4 (#267)
| Benchmark | GPT-6.1 Sol | Llama 3.1-70B |
|---|---|---|
| LMArena Text | 1447 | 1261 |
| LMArena Creative Writing | 1432 | 1232 |
| LMArena Multi-Turn | 1449 | 1256 |
| EQ-Bench Creative Writing | — | 784 |
| WildBench | — | 75.8% |
Frequently asked questions
Is GPT-6.1 Sol better than Llama 3.1-70B?
GPT-6.1 Sol is the stronger model overall, scoring 65.6 to 29.6 on the Noometry Index. Llama 3.1-70B costs 10× less per token, which makes it the better buy when GPT-6.1 Sol's lead doesn't matter for your workload.
Which is cheaper, GPT-6.1 Sol or Llama 3.1-70B?
Llama 3.1-70B is cheaper. It lists at $0.40 per million input tokens and $0.40 per million output tokens; GPT-6.1 Sol lists at $2 and $10.
Is GPT-6.1 Sol or Llama 3.1-70B better for coding?
GPT-6.1 Sol scores higher on coding benchmarks: 63.2 versus 30.3 in the Noometry coding category.
Which has the bigger context window?
GPT-6.1 Sol does, with 1.05M tokens against 128K.
How many benchmarks do GPT-6.1 Sol and Llama 3.1-70B share?
15 benchmarks have published results for both models. GPT-6.1 Sol has 34 scored results on Noometry and Llama 3.1-70B has 35.