Zephyr Base on SWE-bench Verified: score, rank and what it means
Zephyr Base scores 42.4 on SWE-bench Verified, placing it #498 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 Zephyr Base 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, Zephyr Base sits at #498 of 600. The leader, GPT-5.2 Pro, scores 81.7, so the gap to the top is 39.3 points. The median model in this index scores 61.0, which puts Zephyr Base below the midpoint.
Hugging Face models average 37.7 on this benchmark. Zephyr Base is 4.7 points above that provider line, so it is a stronger result than the average Hugging Face model.
Among open-weight models, the average is 55.5. Zephyr Base is 13.1 points below that group. This is the more useful comparison if you are shortlisting within the same tier rather than across the whole index.
Read a 42.4 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 $1.26 per million input tokens, Zephyr Base is below 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 |
|---|---|---|---|---|
| MiniMax-Text 7B | MiniMax | 16384 | $1.10 | 57.7 |
| Hunyuan-Large 8B | Tencent | 4096 | $1.29 | 58.7 |
| Llama 3 Novita 7B | Novita AI | 8192 | $0.92 | 56.3 |
| Llama 3 Replicate 8B | Replicate | 32768 | $1.00 | 57.0 |
| Zephyr Base | Hugging Face | 4096 | $1.26 | 59.5 |
| Firefunction Nano | Fireworks AI | 16384 | $3.07 | 58.1 |
| Llama 3 Anyscale 8B | Anyscale | 32768 | $0.97 | 57.3 |
Other benchmarks for Zephyr Base
| Benchmark | Score | Rank | Percentile | Relative |
|---|---|---|---|---|
| MMLU-Pro | 65.4 | 447 | 26th | |
| GPQA Diamond | 57.2 | 438 | 27th | |
| HumanEval | 64.8 | 443 | 26th | |
| MATH-500 | 62.6 | 440 | 27th | |
| AIME 2025 | 51.0 | 452 | 25th | |
| LiveCodeBench | 47.9 | 468 | 22th | |
| IFEval | 70.3 | 456 | 24th | |
| TruthfulQA | 65.1 | 458 | 24th | |
| HellaSwag | 73.1 | 480 | 20th | |
| MMMU | 54.2 | 506 | 16th | |
| Arena Elo | 1270.3 | 458 | 24th |
FAQ
What score does Zephyr Base get on SWE-bench Verified?
Zephyr Base scores 42.4 on SWE-bench Verified in this index. The benchmark average is 57.5 and the top score is 81.7.
How does Zephyr Base rank on SWE-bench Verified?
It ranks #498 of 600 models, in the 17th percentile. The leader is GPT-5.2 Pro at 81.7.
Is Zephyr Base good at SWE-bench Verified?
It is below the median for this benchmark, so test it carefully before relying on it for this capability. 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 Zephyr Base cost?
Zephyr Base costs $1.26 per million input tokens and $6.45 per million output tokens.