Model comparison
Claude Haiku 4.5 vs Mistral Medium 3.5
Claude Haiku 4.5 and Mistral Medium 3.5 score almost the same on the Noometry Index (39.3 vs 39.6), so choose on price, context window or the category you care about most.
Last verified . 20 shared benchmarks.
Mistral AISummary
- They share 20 benchmarks with published results for both. Claude Haiku 4.5 scores higher in 3 categories and Mistral Medium 3.5 in 6 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in multimodal, where Mistral Medium 3.5 leads 37.6 to 27.0.
- Claude Haiku 4.5 is cheaper at $1 / $5 per million input/output tokens, against $1.50 / $7.50 for Mistral Medium 3.5.
- Mistral Medium 3.5 accepts more context: 262K tokens versus 200K.
- Mistral Medium 3.5 has downloadable open weights; the other is API-only.
Side by side
| Claude Haiku 4.5 | Mistral Medium 3.5 | |
|---|---|---|
| Provider | Anthropic | Mistral AI |
| Noometry Index | 39.3 | 39.6 |
| Released | 2025-10-15 | — |
| Weights | Proprietary | Open |
| Context window | 200K | 262K |
| Max output | 64K | 210K |
| Input $ / M tokens | $1 | $1.50 |
| Output $ / M tokens | $5 | $7.50 |
| Results tracked | 53 | 22 |
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), Mistral Medium 3.5: 35.7 (#208)
| Benchmark | Claude Haiku 4.5 | Mistral Medium 3.5 |
|---|---|---|
| LMArena WebDev | 1330 | 1263 |
| LMArena Coding | 1454 | 1461 |
| SWE-bench Verified (bash only) | 66.6% | — |
| SWE-bench Multilingual | 64.7% | — |
| SciCode | 43.3% | — |
| WeirdML | 45.4% | — |
| ALE-Bench | 653.48 | — |
Agentic & Tool Use Not comparable
Claude Haiku 4.5: 33.5 (#50), Mistral Medium 3.5: —
| Benchmark | Claude Haiku 4.5 | Mistral Medium 3.5 |
|---|---|---|
| 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 Mistral Medium 3.5 leads
Claude Haiku 4.5: 15.1 (#310), Mistral Medium 3.5: 16.6 (#290)
| Benchmark | Claude Haiku 4.5 | Mistral Medium 3.5 |
|---|---|---|
| NYT Connections (extended) | 14.3% | 12.9% |
| LMArena Hard Prompts | 1420 | 1436 |
| Epoch Capabilities Index | 142.42 | 141.42 |
| ARC-AGI-2 | 4% | — |
| Kagi LLM Benchmark | — | 41.4% |
| ARC-AGI-1 | 47.7% | — |
| CritPt | 0% | — |
| Chess Puzzles | 8% | — |
| DTBench | 73.6% | — |
| LMCA | 30.9% | — |
| ForecastBench | 61.4 | — |
Math Claude Haiku 4.5 leads
Claude Haiku 4.5: 43.0 (#69), Mistral Medium 3.5: 36.4 (#113)
| Benchmark | Claude Haiku 4.5 | Mistral Medium 3.5 |
|---|---|---|
| LMArena Math | 1395 | 1432 |
| OTIS Mock AIME 2024-2025 | 66.7% | — |
| Omni-MATH | 56.1% | — |
| MATH Level 5 | 96.4% | — |
| FrontierMath (Feb 2025 set) | 5.9% | — |
| FrontierMath Tier 4 (v1) | 2.1% | — |
Knowledge Mistral Medium 3.5 leads
Claude Haiku 4.5: 37.6 (#146), Mistral Medium 3.5: 39.3 (#123)
| Benchmark | Claude Haiku 4.5 | Mistral Medium 3.5 |
|---|---|---|
| LMArena Expert | 1443 | 1431 |
| GPQA Diamond | 71.2% | — |
| SimpleQA Verified | 13.2% | — |
| MMLU-Pro | 77.7% | — |
| Vectara Hallucination Rate | 9.8% | — |
| GPQA (HELM) | 60.5% | — |
Multimodal Mistral Medium 3.5 leads
Claude Haiku 4.5: 27.0 (#111), Mistral Medium 3.5: 37.6 (#64)
| Benchmark | Claude Haiku 4.5 | Mistral Medium 3.5 |
|---|---|---|
| LMArena Vision | — | 1222 |
| Blueprint-Bench 2 | 0% | — |
| LMArena Document | 1420 | — |
Multilingual Mistral Medium 3.5 leads
Claude Haiku 4.5: 50.1 (#124), Mistral Medium 3.5: 52.1 (#93)
| Benchmark | Claude Haiku 4.5 | Mistral Medium 3.5 |
|---|---|---|
| LMArena Non-English | 1376 | 1405 |
| LMArena Chinese | 1415 | 1443 |
| LMArena French | 1408 | 1448 |
| LMArena German | 1377 | 1453 |
| LMArena Korean | 1346 | 1387 |
| LMArena Russian | 1380 | 1396 |
| LMArena Spanish | 1420 | 1406 |
| LMArena Japanese | 1339 | — |
Instruction Following Mistral Medium 3.5 leads
Claude Haiku 4.5: 71.6 (#144), Mistral Medium 3.5: 74.7 (#87)
| Benchmark | Claude Haiku 4.5 | Mistral Medium 3.5 |
|---|---|---|
| LMArena Instruction Following | 1414 | 1414 |
| IFEval | 80.1% | — |
Long Context Too close to call
Claude Haiku 4.5: 43.6 (#86), Mistral Medium 3.5: 43.2 (#101)
| Benchmark | Claude Haiku 4.5 | Mistral Medium 3.5 |
|---|---|---|
| LMArena Longer Query | 1427 | 1414 |
Writing & Preference Too close to call
Claude Haiku 4.5: 58.1 (#119), Mistral Medium 3.5: 58.6 (#113)
| Benchmark | Claude Haiku 4.5 | Mistral Medium 3.5 |
|---|---|---|
| LMArena Text | 1396 | 1421 |
| LMArena Creative Writing | 1371 | 1372 |
| EQ-Bench 4 | 1064 | 993 |
| LMArena Multi-Turn | 1409 | 1423 |
| WildBench | 83.9% | — |
Frequently asked questions
Is Claude Haiku 4.5 better than Mistral Medium 3.5?
Claude Haiku 4.5 and Mistral Medium 3.5 score almost the same on the Noometry Index (39.3 vs 39.6), so choose on price, context window or the category you care about most.
Which is cheaper, Claude Haiku 4.5 or Mistral Medium 3.5?
Claude Haiku 4.5 is cheaper. It lists at $1 per million input tokens and $5 per million output tokens; Mistral Medium 3.5 lists at $1.50 and $7.50.
Is Claude Haiku 4.5 or Mistral Medium 3.5 better for coding?
Claude Haiku 4.5 scores higher on coding benchmarks: 43.9 versus 35.7 in the Noometry coding category.
Which has the bigger context window?
Mistral Medium 3.5 does, with 262K tokens against 200K.
How many benchmarks do Claude Haiku 4.5 and Mistral Medium 3.5 share?
20 benchmarks have published results for both models. Claude Haiku 4.5 has 53 scored results on Noometry and Mistral Medium 3.5 has 22.