Model comparison
Claude Haiku 4.5 vs Mixtral 8x22B
Claude Haiku 4.5 is the stronger model overall, scoring 39.3 to 26.7 on the Noometry Index.
Last verified . 28 shared benchmarks.
Mistral AISummary
- They share 28 benchmarks with published results for both. Claude Haiku 4.5 scores higher in 8 categories and Mixtral 8x22B in 1 category; 9 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Claude Haiku 4.5 leads 37.6 to 15.1.
- The biggest single-benchmark swing is MATH Level 5: 96.4% for Claude Haiku 4.5 and 24.2% for Mixtral 8x22B.
- Claude Haiku 4.5 is cheaper at $1 / $5 per million input/output tokens, against $2 / $6 for Mixtral 8x22B.
- Claude Haiku 4.5 accepts more context: 200K tokens versus 64K.
- Mixtral 8x22B has downloadable open weights; the other is API-only.
Side by side
| Claude Haiku 4.5 | Mixtral 8x22B | |
|---|---|---|
| Provider | Anthropic | Mistral AI |
| Noometry Index | 39.3 | 26.7 |
| Released | 2025-10-15 | 2024-04-17 |
| Weights | Proprietary | Open |
| Context window | 200K | 64K |
| Max output | 64K | 64K |
| Input $ / M tokens | $1 | $2 |
| Output $ / M tokens | $5 | $6 |
| Results tracked | 53 | 34 |
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: 43.9 (#71), Mixtral 8x22B: 23.8 (#324)
| Benchmark | Claude Haiku 4.5 | Mixtral 8x22B |
|---|---|---|
| WeirdML | 45.4% | 3.2% |
| LMArena Coding | 1454 | 1166 |
| SWE-bench Verified (bash only) | 66.6% | — |
| LMArena WebDev | 1330 | — |
| SWE-bench Multilingual | 64.7% | — |
| SciCode | 43.3% | — |
| BigCodeBench Instruct | — | 40.6% |
| BigCodeBench Complete | — | 50.2% |
| ALE-Bench | 653.48 | — |
| HumanEval+ | — | 72% |
| MBPP+ | — | 64.3% |
Agentic & Tool Use Claude Haiku 4.5 leads
Claude Haiku 4.5: 33.5 (#50), Mixtral 8x22B: 22.8 (#119)
| Benchmark | Claude Haiku 4.5 | Mixtral 8x22B |
|---|---|---|
| Terminal-Bench | 35.5% | — |
| Berkeley Function Calling Leaderboard | 68.7% | — |
| Cybench | — | 7.5% |
| DeepResearch Bench | 45.5% | — |
| BALROG | 31.2% | — |
| ExploitBench | 13.7% | — |
| Vending-Bench 2 | 458.89 | — |
Reasoning Mixtral 8x22B leads
Claude Haiku 4.5: 15.1 (#310), Mixtral 8x22B: 19.1 (#246)
| Benchmark | Claude Haiku 4.5 | Mixtral 8x22B |
|---|---|---|
| LMArena Hard Prompts | 1420 | 1150 |
| DTBench | 73.6% | 55.1% |
| Epoch Capabilities Index | 142.42 | 122 |
| 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% | — |
Math Claude Haiku 4.5 leads
Claude Haiku 4.5: 43.0 (#69), Mixtral 8x22B: 21.2 (#271)
| Benchmark | Claude Haiku 4.5 | Mixtral 8x22B |
|---|---|---|
| Omni-MATH | 56.1% | 16.3% |
| LMArena Math | 1395 | 1184 |
| MATH Level 5 | 96.4% | 24.2% |
| OTIS Mock AIME 2024-2025 | 66.7% | — |
| FrontierMath (Feb 2025 set) | 5.9% | — |
| FrontierMath Tier 4 (v1) | 2.1% | — |
Knowledge Claude Haiku 4.5 leads
Claude Haiku 4.5: 37.6 (#146), Mixtral 8x22B: 15.1 (#288)
| Benchmark | Claude Haiku 4.5 | Mixtral 8x22B |
|---|---|---|
| GPQA Diamond | 71.2% | 34.1% |
| MMLU-Pro | 77.7% | 46% |
| GPQA (HELM) | 60.5% | 33.4% |
| LMArena Expert | 1443 | 1113 |
| SimpleQA Verified | 13.2% | — |
| Vectara Hallucination Rate | 9.8% | — |
| MMLU | — | 77.8% |
Multimodal Not comparable
Claude Haiku 4.5: 27.0 (#111), Mixtral 8x22B: —
| Benchmark | Claude Haiku 4.5 | Mixtral 8x22B |
|---|---|---|
| Blueprint-Bench 2 | 0% | — |
| LMArena Document | 1420 | — |
Multilingual Claude Haiku 4.5 leads
Claude Haiku 4.5: 50.1 (#124), Mixtral 8x22B: 32.9 (#250)
| Benchmark | Claude Haiku 4.5 | Mixtral 8x22B |
|---|---|---|
| LMArena Non-English | 1376 | 1128 |
| LMArena Chinese | 1415 | 1116 |
| LMArena French | 1408 | 1165 |
| LMArena German | 1377 | 1141 |
| LMArena Japanese | 1339 | 1037 |
| LMArena Korean | 1346 | 1056 |
| LMArena Russian | 1380 | 1158 |
| LMArena Spanish | 1420 | 1150 |
Instruction Following Claude Haiku 4.5 leads
Claude Haiku 4.5: 71.6 (#144), Mixtral 8x22B: 57.9 (#261)
| Benchmark | Claude Haiku 4.5 | Mixtral 8x22B |
|---|---|---|
| IFEval | 80.1% | 72.4% |
| LMArena Instruction Following | 1414 | 1147 |
Long Context Claude Haiku 4.5 leads
Claude Haiku 4.5: 43.6 (#86), Mixtral 8x22B: 34.6 (#242)
| Benchmark | Claude Haiku 4.5 | Mixtral 8x22B |
|---|---|---|
| LMArena Longer Query | 1427 | 1144 |
Writing & Preference Claude Haiku 4.5 leads
Claude Haiku 4.5: 58.1 (#119), Mixtral 8x22B: 37.1 (#257)
| Benchmark | Claude Haiku 4.5 | Mixtral 8x22B |
|---|---|---|
| LMArena Text | 1396 | 1162 |
| LMArena Creative Writing | 1371 | 1141 |
| WildBench | 83.9% | 71.1% |
| LMArena Multi-Turn | 1409 | 1130 |
| EQ-Bench 4 | 1064 | — |
Frequently asked questions
Is Claude Haiku 4.5 better than Mixtral 8x22B?
Claude Haiku 4.5 is the stronger model overall, scoring 39.3 to 26.7 on the Noometry Index.
Which is cheaper, Claude Haiku 4.5 or Mixtral 8x22B?
Claude Haiku 4.5 is cheaper. It lists at $1 per million input tokens and $5 per million output tokens; Mixtral 8x22B lists at $2 and $6.
Is Claude Haiku 4.5 or Mixtral 8x22B better for coding?
Claude Haiku 4.5 scores higher on coding benchmarks: 43.9 versus 23.8 in the Noometry coding category.
Which has the bigger context window?
Claude Haiku 4.5 does, with 200K tokens against 64K.
How many benchmarks do Claude Haiku 4.5 and Mixtral 8x22B share?
28 benchmarks have published results for both models. Claude Haiku 4.5 has 53 scored results on Noometry and Mixtral 8x22B has 34.