SmolLM3 8B: pricing, context window and benchmarks
SmolLM3 8B is a small open-weight model from Hugging Face. It offers a 32,768-token context window, costs $0.21 per million input tokens and $0.76 per million output tokens, and averages 44.0 across the index's benchmark suite.
Pricing
SmolLM3 8B costs $0.21 per million input tokens and $0.76 per million output tokens. A blended 3:1 input-to-output mix works out to about $0.35 per million tokens. Cached input is listed at $0.02 per million tokens.
| Item | Price | Notes |
|---|---|---|
| Input | $0.21 | per 1M tokens |
| Output | $0.76 | per 1M tokens |
| Cached input | $0.02 | per 1M tokens |
| Blended 3:1 | $0.35 | estimate per 1M tokens |
| 1M in + 1M out | $0.97 | estimate |
Benchmarks
Scores below are modelled estimates on a 0–100 scale. Use them to compare relative position, not as official vendor results.
| Benchmark | Score | Rank | Percentile | Relative |
|---|---|---|---|---|
| MMLU-Pro | 51.2 | 589 | 2th | |
| GPQA Diamond | 38.9 | 589 | 2th | |
| SWE-bench Verified | 27.8 | 586 | 2th | |
| HumanEval | 49.0 | 581 | 3th | |
| MATH-500 | 44.4 | 580 | 3th | |
| AIME 2025 | 26.2 | 591 | 2th | |
| LiveCodeBench | 31.3 | 581 | 3th | |
| IFEval | 56.3 | 589 | 2th | |
| TruthfulQA | 50.6 | 589 | 2th | |
| HellaSwag | 66.2 | 576 | 4th | |
| MMMU | 41.8 | 590 | 2th | |
| Arena Elo | 1153.0 | 584 | 3th |
What SmolLM3 8B is good for
SmolLM3 8B is a small model. That makes it a good fit for classification, extraction, routing, summarization and other high-volume jobs where latency and cost dominate. It is not the right pick for open-ended frontier reasoning, but at $0.21 per million input tokens it can handle a large share of production traffic.
Strengths
- Input price of $0.21 per million tokens is at or below the index median.
- Open weights make self-hosting, fine-tuning and data-residency review possible.
Trade-offs
- Average benchmark score is below the index median; test it on your own task.
- Less reliable on open-ended reasoning and complex multi-step instructions.
How it compares
| Model | Provider | Context | Input / 1M | Avg score |
|---|---|---|---|---|
| Phi-3.5 1.5B | Microsoft | 32768 | $0.25 | 44.5 |
| SmolLM3 7B | Hugging Face | 16384 | $0.19 | 44.3 |
| StableLM 2 7B | Stability AI | 8192 | $0.28 | 44.3 |
| OLMo 2 1.5B | Allen Institute for AI | 16384 | $0.28 | 44.0 |
| SmolLM3 8B | Hugging Face | 32768 | $0.21 | 44.0 |
| GPT-NeoX 8B | EleutherAI | 16384 | $0.25 | 43.7 |
FAQ
How much does SmolLM3 8B cost?
SmolLM3 8B is listed at $0.21 per million input tokens and $0.76 per million output tokens. Cached input is $0.021 per million tokens. A blended 3:1 input-to-output mix is about $0.35 per million tokens.
What is the context window of SmolLM3 8B?
SmolLM3 8B has a context window of 32,768 tokens and can emit up to 16,384 output tokens per request in this index.
Is SmolLM3 8B open weights?
Yes. SmolLM3 8B is listed as an open-weight model under a open weights licence.
How does SmolLM3 8B score on benchmarks?
SmolLM3 8B averages 44.0 across the scored benchmarks in this index, ranking #586 of 600 models. Its strongest relative result is Arena Elo at 1153.0.
What is SmolLM3 8B best for?
SmolLM3 8B is a small model. That makes it a good fit for classification, extraction, routing, summarization and other high-volume jobs where latency and cost dominate. It is not the right pick for open-ended frontier reasoning, but at $0.21 per million input tokens it can handle a large share of production traffic.