Llama 3.1 on SWE-bench Verified: score, rank and what it means
Llama 3.1 scores 67.9 on SWE-bench Verified, placing it #147 of 600 models in the index. The benchmark average is 57.5 and the leader is GPT-5.2 Pro at 81.7.
Score distribution
The chart shows the top 10 models on SWE-bench Verified, with Llama 3.1 highlighted. Longer bars mean higher scores.
Top 10 leaderboard
| # | Model | Provider | Context | Input / 1M | Avg score |
|---|---|---|---|---|---|
| 1 | GPT-5.2 Pro | OpenAI | 2000000 | $21.32 | 89.6 |
| 2 | Claude Opus 4.5 Pro | Anthropic | 200000 | $20.98 | 89.1 |
| 3 | GPT-5.2 Max | OpenAI | 1000000 | $21.39 | 89.2 |
| 4 | Claude Sonnet 4.5 Max | Anthropic | 1000000 | $19.90 | 87.2 |
| 5 | GPT-5.2 | OpenAI | 2000000 | $19.71 | 88.0 |
| 6 | GPT-5.1 Pro | OpenAI | 200000 | $19.77 | 87.8 |
| 7 | o4 Max | OpenAI | 2000000 | $19.51 | 86.2 |
| 8 | Claude Sonnet 4.5 Reasoning | Anthropic | 400000 | $19.48 | 87.7 |
| 9 | Claude Opus 4.5 Max | Anthropic | 1000000 | $20.90 | 87.8 |
| 10 | Claude Opus 4.5 Reasoning | Anthropic | 2000000 | $20.91 | 88.2 |
What this score means
On SWE-bench Verified, Llama 3.1 sits at #147 of 600. The leader, GPT-5.2 Pro, scores 81.7, so the gap to the top is 13.8 points. The median model in this index scores 61.0, which puts Llama 3.1 above the midpoint.
Meta AI models average 56.9 on this benchmark. Llama 3.1 is 11.0 points above that provider line, so it is a stronger result than the average Meta AI model.
Among multimodal models, the average is 66.4. Llama 3.1 is 1.5 points above that group. This is the more useful comparison if you are shortlisting within the same tier rather than across the whole index.
Read a 67.9 as a relative signal, not an absolute guarantee. Benchmark scores depend on prompt format, evaluation harness and contamination controls. Use this page to narrow the shortlist, then test the model on your own data.
Price context
At $4.16 per million input tokens, Llama 3.1 is above the median input price of $4.00 across the 600 models scored on SWE-bench Verified. The models immediately around it in the ranking are shown below so you can compare score and price together.
| Model | Provider | Context | Input / 1M | Avg score |
|---|---|---|---|---|
| Nova Pro Pro | Amazon | 200000 | $13.03 | 79.5 |
| Claude Sonnet 4.5 Mini | Anthropic | 32768 | $11.43 | 76.5 |
| ERNIE 4.0 Max | Baidu | 32768 | $12.40 | 78.9 |
| Gemini 3 Pro Mini | Google DeepMind | 128000 | $12.27 | 78.1 |
| Llama 3.1 | Meta AI | 200000 | $4.16 | 76.3 |
| Llama 4 Maverick Base | Meta AI | 128000 | $4.68 | 79.1 |
| Hunyuan-Large | Tencent | 65536 | $4.33 | 78.2 |
Other benchmarks for Llama 3.1
| Benchmark | Score | Rank | Percentile | Relative |
|---|---|---|---|---|
| MMLU-Pro | 78.8 | 220 | 63th | |
| GPQA Diamond | 69.8 | 272 | 55th | |
| HumanEval | 81.8 | 189 | 69th | |
| MATH-500 | 82.8 | 150 | 75th | |
| AIME 2025 | 69.5 | 268 | 55th | |
| LiveCodeBench | 66.7 | 258 | 57th | |
| IFEval | 82.3 | 267 | 56th | |
| TruthfulQA | 78.4 | 240 | 60th | |
| HellaSwag | 87.2 | 166 | 72th | |
| MMMU | 74.2 | 180 | 70th | |
| Arena Elo | 1407.6 | 187 | 69th |
FAQ
What score does Llama 3.1 get on SWE-bench Verified?
Llama 3.1 scores 67.9 on SWE-bench Verified in this index. The benchmark average is 57.5 and the top score is 81.7.
How does Llama 3.1 rank on SWE-bench Verified?
It ranks #147 of 600 models, in the 76th percentile. The leader is GPT-5.2 Pro at 81.7.
Is Llama 3.1 good at SWE-bench Verified?
Yes, relative to the index: it is above the median and inside the top half of scores. The result should be read alongside its price and context window.
How is the SWE-bench Verified score calculated?
SWE-bench Verified is a coding benchmark. Scores in this index are modelled estimates on a 0–100 scale (or Elo for Arena), derived from capability tier and benchmark difficulty. They are not official leaderboard results.
What does Llama 3.1 cost?
Llama 3.1 costs $4.16 per million input tokens and $15.79 per million output tokens.