# Devstral Small 2505 vs Llama 3-70B

> Devstral Small 2505 is the stronger model overall, scoring 33.9 to 28.5 on the Noometry Index.

- Canonical page: https://noometry.com/compare/devstral-small-vs-llama-3-70b
- Last updated: 2026-10-10
- Shared benchmarks: 1

## Summary

- They share 1 benchmark with published results for both. Devstral Small 2505 scores higher in 2 categories and Llama 3-70B in 0 categories; 2 gaps are clear of the uncertainty.
- The widest gap is in coding, where Devstral Small 2505 leads 38.6 to 35.3.

## Snapshot

| | Devstral Small 2505 | Llama 3-70B |
|---|---|---|
| Provider | Mistral AI | Meta |
| Noometry Index | 33.9 | 28.5 |
| Rank | 228 | 317 |
| Context | 128K | — |
| Input $/M | $0.10 | — |
| Output $/M | $0.30 | — |
| Weights | Open | Open |

## Coding

- Devstral Small 2505: 38.6 (#160)
- Llama 3-70B: 35.3 (#215)

| Benchmark | Devstral Small 2505 | Llama 3-70B |
|---|---|---|
| SWE-bench Verified (bash only) | 56.4% | — |
| SciCode | 28.8% | — |
| BigCodeBench Instruct | — | 43.6% |
| LMArena Coding | — | 1206 |
| BigCodeBench Complete | — | 54.5% |
| HumanEval+ | — | 72% |
| MBPP+ | — | 69% |

## Agentic & Tool Use

- Devstral Small 2505: —
- Llama 3-70B: 20.9 (#132)

| Benchmark | Devstral Small 2505 | Llama 3-70B |
|---|---|---|
| Cybench | — | 5% |

## Reasoning

- Devstral Small 2505: 19.1 (#243)
- Llama 3-70B: 17.4 (#284)

| Benchmark | Devstral Small 2505 | Llama 3-70B |
|---|---|---|
| Kagi LLM Benchmark | 37.7% | 35.1% |
| CritPt | 0% | — |
| LMArena Hard Prompts | — | 1195 |
| DTBench | — | 54.2% |
| Epoch Capabilities Index | — | 122.91 |
| ForecastBench | — | 57.1 |
| WinoGrande | — | 83.5% |

## Math

- Devstral Small 2505: —
- Llama 3-70B: 12.0 (#299)

| Benchmark | Devstral Small 2505 | Llama 3-70B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 4.3% |
| LMArena Math | — | 1218 |
| MATH Level 5 | — | 22.6% |

## Knowledge

- Devstral Small 2505: —
- Llama 3-70B: 20.8 (#272)

| Benchmark | Devstral Small 2505 | Llama 3-70B |
|---|---|---|
| GPQA Diamond | — | 40.6% |
| LMArena Expert | — | 1149 |
| MMLU | — | 79.3% |

## Multilingual

- Devstral Small 2505: —
- Llama 3-70B: 33.8 (#246)

| Benchmark | Devstral Small 2505 | Llama 3-70B |
|---|---|---|
| LMArena Non-English | — | 1142 |
| LMArena Chinese | — | 1114 |
| LMArena French | — | 1231 |
| LMArena German | — | 1169 |
| LMArena Japanese | — | 1017 |
| LMArena Korean | — | 1017 |
| LMArena Russian | — | 1159 |
| LMArena Spanish | — | 1241 |

## Instruction Following

- Devstral Small 2505: —
- Llama 3-70B: 62.8 (#233)

| Benchmark | Devstral Small 2505 | Llama 3-70B |
|---|---|---|
| LMArena Instruction Following | — | 1194 |

## Long Context

- Devstral Small 2505: —
- Llama 3-70B: 35.6 (#235)

| Benchmark | Devstral Small 2505 | Llama 3-70B |
|---|---|---|
| LMArena Longer Query | — | 1174 |

## Writing & Preference

- Devstral Small 2505: —
- Llama 3-70B: 43.0 (#225)

| Benchmark | Devstral Small 2505 | Llama 3-70B |
|---|---|---|
| LMArena Text | — | 1221 |
| LMArena Creative Writing | — | 1210 |
| LMArena Multi-Turn | — | 1223 |

## FAQ

### Is Devstral Small 2505 better than Llama 3-70B?

Devstral Small 2505 is the stronger model overall, scoring 33.9 to 28.5 on the Noometry Index.

### Is Devstral Small 2505 or Llama 3-70B better for coding?

Devstral Small 2505 scores higher on coding benchmarks: 38.6 versus 35.3 in the Noometry coding category.

### How many benchmarks do Devstral Small 2505 and Llama 3-70B share?

1 benchmark has published results for both models. Devstral Small 2505 has 4 scored results on Noometry and Llama 3-70B has 31.