Model comparison
Claude Haiku 4.5 vs Mixtral 8x7B
Claude Haiku 4.5 is the stronger model overall, scoring 39.5 to 27.1 on the Noometry Index. Mixtral 8x7B costs 2.9× less per token, which makes it the better buy when Claude Haiku 4.5's lead doesn't matter for your workload.
Last verified . 27 shared benchmarks.
Mistral AISummary
- They share 27 benchmarks with published results for both. Claude Haiku 4.5 scores higher in 7 categories and Mixtral 8x7B in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Claude Haiku 4.5 leads 37.7 to 11.0.
- The biggest single-benchmark swing is MATH Level 5: 96.4% for Claude Haiku 4.5 and 10% for Mixtral 8x7B.
- Mixtral 8x7B is cheaper at $0.70 / $0.70 per million input/output tokens, against $1 / $5 for Claude Haiku 4.5.
- Claude Haiku 4.5 accepts more context: 200K tokens versus 32K.
- Mixtral 8x7B has downloadable open weights; the other is API-only.
Side by side
| Claude Haiku 4.5 | Mixtral 8x7B | |
|---|---|---|
| Provider | Anthropic | Mistral AI |
| Noometry Index | 39.5 | 27.1 |
| Released | 2025-10-15 | 2023-12-11 |
| Weights | Proprietary | Open |
| Context window | 200K | 32K |
| Max output | 64K | 32K |
| Input $ / M tokens | $1 | $0.70 |
| Output $ / M tokens | $5 | $0.70 |
| Results tracked | 53 | 38 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Haiku 4.5 leads
Claude Haiku 4.5: 44.0 (#78), Mixtral 8x7B: 32.8 (#269)
| Benchmark | Claude Haiku 4.5 | Mixtral 8x7B |
|---|---|---|
| LMArena Coding | 1453 | 1126 |
| 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 | — |
| HumanEval+ | — | 39.6% |
| MBPP+ | — | 49.7% |
Agentic & Tool Use Not comparable
Claude Haiku 4.5: 33.6 (#52), Mixtral 8x7B: —
| Benchmark | Claude Haiku 4.5 | Mixtral 8x7B |
|---|---|---|
| Terminal-Bench | 35.5% | — |
| Berkeley Function Calling Leaderboard | 68.7% | — |
| DeepResearch Bench | 45.5% | — |
| BALROG | 31.2% | — |
| ExploitBench | 13.7% | — |
| Vending-Bench 2 | 458.89 | — |
Reasoning Mixtral 8x7B leads
Claude Haiku 4.5: 15.1 (#320), Mixtral 8x7B: 18.2 (#285)
| Benchmark | Claude Haiku 4.5 | Mixtral 8x7B |
|---|---|---|
| LMArena Hard Prompts | 1420 | 1115 |
| DTBench | 73.6% | 49.6% |
| Epoch Capabilities Index | 142.41 | 118.47 |
| ForecastBench | 61.4 | 56.3 |
| ARC-AGI-2 | 4% | — |
| NYT Connections (extended) | 14.3% | — |
| ARC-AGI-1 | 47.7% | — |
| CritPt | 0% | — |
| Chess Puzzles | 8% | — |
| LMCA | 30.9% | — |
| Adversarial NLI | — | 55.2% |
| HellaSwag | — | 86.7% |
| PIQA | — | 83.6% |
| WinoGrande | — | 77.2% |
Math Claude Haiku 4.5 leads
Claude Haiku 4.5: 44.9 (#78), Mixtral 8x7B: 18.8 (#289)
| Benchmark | Claude Haiku 4.5 | Mixtral 8x7B |
|---|---|---|
| Omni-MATH | 56.1% | 10.5% |
| LMArena Math | 1396 | 1147 |
| MATH Level 5 | 96.4% | 10% |
| OTIS Mock AIME 2024-2025 | 66.7% | — |
| FrontierMath (Feb 2025 set) | 5.9% | — |
| FrontierMath Tier 4 (v1) | 2.1% | — |
| GSM8K | — | 74.4% |
Knowledge Claude Haiku 4.5 leads
Claude Haiku 4.5: 37.7 (#153), Mixtral 8x7B: 11.0 (#301)
| Benchmark | Claude Haiku 4.5 | Mixtral 8x7B |
|---|---|---|
| GPQA Diamond | 71.2% | 30.6% |
| MMLU-Pro | 77.7% | 33.5% |
| GPQA (HELM) | 60.5% | 29.6% |
| LMArena Expert | 1442 | 1088 |
| SimpleQA Verified | 13.2% | — |
| Vectara Hallucination Rate | 9.8% | — |
| ARC (AI2) Challenge | — | 87.3% |
| MMLU | — | 70.6% |
| OpenBookQA | — | 85.8% |
| TriviaQA | — | 82.2% |
Multimodal Not comparable
Claude Haiku 4.5: 26.8 (#118), Mixtral 8x7B: —
| Benchmark | Claude Haiku 4.5 | Mixtral 8x7B |
|---|---|---|
| Blueprint-Bench 2 | 0% | — |
| LMArena Document | 1420 | — |
Multilingual Claude Haiku 4.5 leads
Claude Haiku 4.5: 49.9 (#129), Mixtral 8x7B: 29.6 (#266)
| Benchmark | Claude Haiku 4.5 | Mixtral 8x7B |
|---|---|---|
| LMArena Non-English | 1377 | 1077 |
| LMArena Chinese | 1417 | 1055 |
| LMArena French | 1408 | 1166 |
| LMArena German | 1375 | 1114 |
| LMArena Japanese | 1339 | 931 |
| LMArena Korean | 1347 | 968 |
| LMArena Russian | 1381 | 1090 |
| LMArena Spanish | 1420 | 1111 |
Instruction Following Claude Haiku 4.5 leads
Claude Haiku 4.5: 71.4 (#149), Mixtral 8x7B: 51.0 (#297)
| Benchmark | Claude Haiku 4.5 | Mixtral 8x7B |
|---|---|---|
| IFEval | 80.1% | 57.5% |
| LMArena Instruction Following | 1414 | 1109 |
Long Context Claude Haiku 4.5 leads
Claude Haiku 4.5: 43.6 (#92), Mixtral 8x7B: 33.4 (#260)
| Benchmark | Claude Haiku 4.5 | Mixtral 8x7B |
|---|---|---|
| LMArena Longer Query | 1427 | 1103 |
Writing & Preference Claude Haiku 4.5 leads
Claude Haiku 4.5: 57.9 (#123), Mixtral 8x7B: 34.2 (#270)
| Benchmark | Claude Haiku 4.5 | Mixtral 8x7B |
|---|---|---|
| LMArena Text | 1396 | 1132 |
| LMArena Creative Writing | 1372 | 1109 |
| WildBench | 83.9% | 67.3% |
| LMArena Multi-Turn | 1409 | 1115 |
| EQ-Bench 4 | 1064 | — |
Frequently asked questions
Is Claude Haiku 4.5 better than Mixtral 8x7B?
Claude Haiku 4.5 is the stronger model overall, scoring 39.5 to 27.1 on the Noometry Index. Mixtral 8x7B costs 2.9× 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 Mixtral 8x7B?
Mixtral 8x7B is cheaper. It lists at $0.70 per million input tokens and $0.70 per million output tokens; Claude Haiku 4.5 lists at $1 and $5.
Is Claude Haiku 4.5 or Mixtral 8x7B better for coding?
Claude Haiku 4.5 scores higher on coding benchmarks: 44.0 versus 32.8 in the Noometry coding category.
Which has the bigger context window?
Claude Haiku 4.5 does, with 200K tokens against 32K.
How many benchmarks do Claude Haiku 4.5 and Mixtral 8x7B share?
27 benchmarks have published results for both models. Claude Haiku 4.5 has 53 scored results on Noometry and Mixtral 8x7B has 38.