# Mistral 7B vs Step 3.5 Flash

> Step 3.5 Flash is the stronger model overall, scoring 42.3 to 23.0 on the Noometry Index.

- Canonical page: https://noometry.com/compare/mistral-7b-vs-step-3-5-flash
- Last updated: 2026-10-11
- Shared benchmarks: 16

## Summary

- They share 16 benchmarks with published results for both. Mistral 7B scores higher in 0 categories and Step 3.5 Flash in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Step 3.5 Flash leads 42.6 to 8.1.
- Step 3.5 Flash is cheaper at $0.10 / $0.30 per million input/output tokens, against $0.25 / $0.25 for Mistral 7B.
- Step 3.5 Flash accepts more context: 256K tokens versus 8K.

## Snapshot

| | Mistral 7B | Step 3.5 Flash |
|---|---|---|
| Provider | Mistral AI | StepFun |
| Noometry Index | 23.0 | 42.3 |
| Rank | 351 | 116 |
| Context | 8K | 256K |
| Input $/M | $0.25 | $0.10 |
| Output $/M | $0.25 | $0.30 |
| Weights | Open | Open |

## Coding

- Mistral 7B: 26.4 (#326)
- Step 3.5 Flash: 42.4 (#105)

| Benchmark | Mistral 7B | Step 3.5 Flash |
|---|---|---|
| LMArena Coding | 1082 | 1436 |
| BigCodeBench Instruct | 19.5% | — |
| BigCodeBench Complete | 27.3% | — |
| HumanEval+ | 36% | — |
| MBPP+ | 42.1% | — |

## Reasoning

- Mistral 7B: 13.1 (#336)
- Step 3.5 Flash: 22.2 (#202)

| Benchmark | Mistral 7B | Step 3.5 Flash |
|---|---|---|
| LMArena Hard Prompts | 1067 | 1411 |
| NYT Connections (extended) | — | 28.4% |
| Chess Puzzles | 0% | — |
| DTBench | 42.5% | — |
| Adversarial NLI | 47.1% | — |
| BIG-Bench Hard | 56.1% | — |
| Epoch Capabilities Index | 112.21 | — |
| HellaSwag | 81% | — |
| PIQA | 83% | — |
| WinoGrande | 75.3% | — |

## Math

- Mistral 7B: 8.1 (#325)
- Step 3.5 Flash: 42.6 (#84)

| Benchmark | Mistral 7B | Step 3.5 Flash |
|---|---|---|
| LMArena Math | 1085 | 1408 |
| MathArena Final-Answer Competitions | — | 66.8% |
| OTIS Mock AIME 2024-2025 | 0.3% | — |
| MATH Level 5 | 3.7% | — |
| GSM8K | 54.4% | — |

## Knowledge

- Mistral 7B: 7.4 (#311)
- Step 3.5 Flash: 39.6 (#132)

| Benchmark | Mistral 7B | Step 3.5 Flash |
|---|---|---|
| LMArena Expert | 1036 | 1421 |
| GPQA Diamond | 15.2% | — |
| ARC (AI2) Challenge | 78.6% | — |
| BoolQ | 87.4% | — |
| MMLU | 62.5% | — |
| OpenBookQA | 79.8% | — |
| TriviaQA | 75.2% | — |

## Multilingual

- Mistral 7B: 25.8 (#283)
- Step 3.5 Flash: 50.5 (#119)

| Benchmark | Mistral 7B | Step 3.5 Flash |
|---|---|---|
| LMArena Non-English | 1012 | 1385 |
| LMArena Chinese | 1009 | 1447 |
| LMArena French | 1037 | 1421 |
| LMArena German | 987 | 1405 |
| LMArena Japanese | 878 | 1354 |
| LMArena Russian | 1018 | 1385 |
| LMArena Spanish | 1026 | 1419 |
| LMArena Korean | — | 1352 |

## Instruction Following

- Mistral 7B: 54.2 (#280)
- Step 3.5 Flash: 73.1 (#124)

| Benchmark | Mistral 7B | Step 3.5 Flash |
|---|---|---|
| LMArena Instruction Following | 1060 | 1385 |

## Long Context

- Mistral 7B: 32.2 (#271)
- Step 3.5 Flash: 42.8 (#117)

| Benchmark | Mistral 7B | Step 3.5 Flash |
|---|---|---|
| LMArena Longer Query | 1060 | 1402 |

## Writing & Preference

- Mistral 7B: 30.7 (#286)
- Step 3.5 Flash: 58.8 (#113)

| Benchmark | Mistral 7B | Step 3.5 Flash |
|---|---|---|
| LMArena Text | 1090 | 1403 |
| LMArena Creative Writing | 1068 | 1357 |
| LMArena Multi-Turn | 1062 | 1405 |

## FAQ

### Is Mistral 7B better than Step 3.5 Flash?

Step 3.5 Flash is the stronger model overall, scoring 42.3 to 23.0 on the Noometry Index.

### Which is cheaper, Mistral 7B or Step 3.5 Flash?

Step 3.5 Flash is cheaper. It lists at $0.10 per million input tokens and $0.30 per million output tokens; Mistral 7B lists at $0.25 and $0.25.

### Is Mistral 7B or Step 3.5 Flash better for coding?

Step 3.5 Flash scores higher on coding benchmarks: 42.4 versus 26.4 in the Noometry coding category.

### Which has the bigger context window?

Step 3.5 Flash does, with 256K tokens against 8K.

### How many benchmarks do Mistral 7B and Step 3.5 Flash share?

16 benchmarks have published results for both models. Mistral 7B has 37 scored results on Noometry and Step 3.5 Flash has 19.