# Claude Haiku 4.5 vs Ministral 8B

> Claude Haiku 4.5 is the stronger model overall, scoring 39.5 to 28.2 on the Noometry Index. Ministral 8B costs 13× less per token, which makes it the better buy when Claude Haiku 4.5's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/claude-haiku-4-5-vs-ministral-8b
- Last updated: 2026-10-10
- Shared benchmarks: 17

## Summary

- They share 17 benchmarks with published results for both. Claude Haiku 4.5 scores higher in 8 categories and Ministral 8B in 1 category; 9 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Claude Haiku 4.5 leads 37.7 to 12.6.
- The biggest single-benchmark swing is MATH Level 5: 96.4% for Claude Haiku 4.5 and 14.9% for Ministral 8B.
- Ministral 8B is cheaper at $0.15 / $0.15 per million input/output tokens, against $1 / $5 for Claude Haiku 4.5.
- Ministral 8B accepts more context: 262K tokens versus 200K.
- Ministral 8B has downloadable open weights; the other is API-only.

## Snapshot

| | Claude Haiku 4.5 | Ministral 8B |
|---|---|---|
| Provider | Anthropic | Mistral AI |
| Noometry Index | 39.5 | 28.2 |
| Rank | 165 | 325 |
| Context | 200K | 262K |
| Input $/M | $1 | $0.15 |
| Output $/M | $5 | $0.15 |
| Weights | Proprietary | Open |

## Coding

- Claude Haiku 4.5: 44.0 (#78)
- Ministral 8B: 35.0 (#230)

| Benchmark | Claude Haiku 4.5 | Ministral 8B |
|---|---|---|
| LMArena Coding | 1453 | 1202 |
| SWE-bench Verified (bash only) | 66.6% | — |
| LMArena WebDev | 1330 | — |
| SWE-bench Multilingual | 64.7% | — |
| SciCode | 43.3% | — |
| WeirdML | 45.4% | — |
| ALE-Bench | 653.48 | — |

## Agentic & Tool Use

- Claude Haiku 4.5: 33.6 (#52)
- Ministral 8B: 16.4 (#148)

| Benchmark | Claude Haiku 4.5 | Ministral 8B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 68.7% | 11.1% |
| Terminal-Bench | 35.5% | — |
| DeepResearch Bench | 45.5% | — |
| BALROG | 31.2% | — |
| ExploitBench | 13.7% | — |
| Vending-Bench 2 | 458.89 | — |

## Reasoning

- Claude Haiku 4.5: 15.1 (#320)
- Ministral 8B: 18.4 (#281)

| Benchmark | Claude Haiku 4.5 | Ministral 8B |
|---|---|---|
| LMArena Hard Prompts | 1420 | 1191 |
| DTBench | 73.6% | 45.7% |
| ARC-AGI-2 | 4% | — |
| NYT Connections (extended) | 14.3% | — |
| ARC-AGI-1 | 47.7% | — |
| CritPt | 0% | — |
| Chess Puzzles | 8% | — |
| LMCA | 30.9% | — |
| Epoch Capabilities Index | 142.41 | — |
| ForecastBench | 61.4 | — |

## Math

- Claude Haiku 4.5: 44.9 (#78)
- Ministral 8B: 25.7 (#267)

| Benchmark | Claude Haiku 4.5 | Ministral 8B |
|---|---|---|
| LMArena Math | 1396 | 1188 |
| MATH Level 5 | 96.4% | 14.9% |
| OTIS Mock AIME 2024-2025 | 66.7% | — |
| Omni-MATH | 56.1% | — |
| FrontierMath (Feb 2025 set) | 5.9% | — |
| FrontierMath Tier 4 (v1) | 2.1% | — |

## Knowledge

- Claude Haiku 4.5: 37.7 (#153)
- Ministral 8B: 12.6 (#297)

| Benchmark | Claude Haiku 4.5 | Ministral 8B |
|---|---|---|
| GPQA Diamond | 71.2% | 27.1% |
| Vectara Hallucination Rate | 9.8% | 7.4% |
| LMArena Expert | 1442 | 1170 |
| SimpleQA Verified | 13.2% | — |
| MMLU-Pro | 77.7% | — |
| GPQA (HELM) | 60.5% | — |

## Multimodal

- Claude Haiku 4.5: 26.8 (#118)
- Ministral 8B: —

| Benchmark | Claude Haiku 4.5 | Ministral 8B |
|---|---|---|
| Blueprint-Bench 2 | 0% | — |
| LMArena Document | 1420 | — |

## Multilingual

- Claude Haiku 4.5: 49.9 (#129)
- Ministral 8B: 35.1 (#247)

| Benchmark | Claude Haiku 4.5 | Ministral 8B |
|---|---|---|
| LMArena Non-English | 1377 | 1165 |
| LMArena Chinese | 1417 | 1193 |
| LMArena Russian | 1381 | 1195 |
| LMArena French | 1408 | — |
| LMArena German | 1375 | — |
| LMArena Japanese | 1339 | — |
| LMArena Korean | 1347 | — |
| LMArena Spanish | 1420 | — |

## Instruction Following

- Claude Haiku 4.5: 71.4 (#149)
- Ministral 8B: 60.5 (#250)

| Benchmark | Claude Haiku 4.5 | Ministral 8B |
|---|---|---|
| LMArena Instruction Following | 1414 | 1161 |
| IFEval | 80.1% | — |

## Long Context

- Claude Haiku 4.5: 43.6 (#92)
- Ministral 8B: 36.7 (#227)

| Benchmark | Claude Haiku 4.5 | Ministral 8B |
|---|---|---|
| LMArena Longer Query | 1427 | 1212 |

## Writing & Preference

- Claude Haiku 4.5: 57.9 (#123)
- Ministral 8B: 39.6 (#246)

| Benchmark | Claude Haiku 4.5 | Ministral 8B |
|---|---|---|
| LMArena Text | 1396 | 1191 |
| LMArena Creative Writing | 1372 | 1175 |
| LMArena Multi-Turn | 1409 | 1166 |
| WildBench | 83.9% | — |
| EQ-Bench 4 | 1064 | — |

## FAQ

### Is Claude Haiku 4.5 better than Ministral 8B?

Claude Haiku 4.5 is the stronger model overall, scoring 39.5 to 28.2 on the Noometry Index. Ministral 8B costs 13× less per token, which makes it the better buy when Claude Haiku 4.5's lead doesn't matter for your workload.

### Which is cheaper, Claude Haiku 4.5 or Ministral 8B?

Ministral 8B is cheaper. It lists at $0.15 per million input tokens and $0.15 per million output tokens; Claude Haiku 4.5 lists at $1 and $5.

### Is Claude Haiku 4.5 or Ministral 8B better for coding?

Claude Haiku 4.5 scores higher on coding benchmarks: 44.0 versus 35.0 in the Noometry coding category.

### Which has the bigger context window?

Ministral 8B does, with 262K tokens against 200K.

### How many benchmarks do Claude Haiku 4.5 and Ministral 8B share?

17 benchmarks have published results for both models. Claude Haiku 4.5 has 53 scored results on Noometry and Ministral 8B has 17.