Model comparison
Claude Haiku 4.5 vs Magistral Medium
Claude Haiku 4.5 is the stronger model overall, scoring 39.3 to 34.8 on the Noometry Index.
Last verified . 21 shared benchmarks.
Mistral AISummary
- They share 21 benchmarks with published results for both. Claude Haiku 4.5 scores higher in 8 categories and Magistral Medium in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Claude Haiku 4.5 leads 58.1 to 46.5.
- The biggest single-benchmark swing is ARC-AGI-1: 47.7% for Claude Haiku 4.5 and 6.1% for Magistral Medium.
- Claude Haiku 4.5 is cheaper at $1 / $5 per million input/output tokens, against $2 / $5 for Magistral Medium.
- Claude Haiku 4.5 accepts more context: 200K tokens versus 128K.
- Magistral Medium has downloadable open weights; the other is API-only.
Side by side
| Claude Haiku 4.5 | Magistral Medium | |
|---|---|---|
| Provider | Anthropic | Mistral AI |
| Noometry Index | 39.3 | 34.8 |
| Released | 2025-10-15 | 2025-03-17 |
| Weights | Proprietary | Open |
| Context window | 200K | 128K |
| Max output | 64K | 16K |
| Input $ / M tokens | $1 | $2 |
| Output $ / M tokens | $5 | $5 |
| 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), Magistral Medium: 38.6 (#161)
| Benchmark | Claude Haiku 4.5 | Magistral Medium |
|---|---|---|
| SciCode | 43.3% | 39.2% |
| LMArena Coding | 1454 | 1319 |
| SWE-bench Verified (bash only) | 66.6% | — |
| LMArena WebDev | 1330 | — |
| SWE-bench Multilingual | 64.7% | — |
| WeirdML | 45.4% | — |
| ALE-Bench | 653.48 | — |
Agentic & Tool Use Not comparable
Claude Haiku 4.5: 33.5 (#50), Magistral Medium: —
| Benchmark | Claude Haiku 4.5 | Magistral Medium |
|---|---|---|
| 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 Claude Haiku 4.5 leads
Claude Haiku 4.5: 15.1 (#310), Magistral Medium: 8.7 (#342)
| Benchmark | Claude Haiku 4.5 | Magistral Medium |
|---|---|---|
| ARC-AGI-2 | 4% | 0% |
| ARC-AGI-1 | 47.7% | 6.1% |
| CritPt | 0% | 0.3% |
| LMArena Hard Prompts | 1420 | 1267 |
| Kagi LLM Benchmark | — | 16.2% |
| NYT Connections (extended) | 14.3% | — |
| Chess Puzzles | 8% | — |
| DTBench | 73.6% | — |
| LMCA | 30.9% | — |
| Epoch Capabilities Index | 142.42 | — |
| ForecastBench | 61.4 | — |
Math Claude Haiku 4.5 leads
Claude Haiku 4.5: 43.0 (#69), Magistral Medium: 32.4 (#187)
| Benchmark | Claude Haiku 4.5 | Magistral Medium |
|---|---|---|
| LMArena Math | 1395 | 1249 |
| 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 Claude Haiku 4.5 leads
Claude Haiku 4.5: 37.6 (#146), Magistral Medium: 32.9 (#199)
| Benchmark | Claude Haiku 4.5 | Magistral Medium |
|---|---|---|
| LMArena Expert | 1443 | 1222 |
| GPQA Diamond | 71.2% | — |
| SimpleQA Verified | 13.2% | — |
| MMLU-Pro | 77.7% | — |
| Vectara Hallucination Rate | 9.8% | — |
| GPQA (HELM) | 60.5% | — |
Multimodal Not comparable
Claude Haiku 4.5: 27.0 (#111), Magistral Medium: —
| Benchmark | Claude Haiku 4.5 | Magistral Medium |
|---|---|---|
| Blueprint-Bench 2 | 0% | — |
| LMArena Document | 1420 | — |
Multilingual Claude Haiku 4.5 leads
Claude Haiku 4.5: 50.1 (#124), Magistral Medium: 39.8 (#219)
| Benchmark | Claude Haiku 4.5 | Magistral Medium |
|---|---|---|
| LMArena Non-English | 1376 | 1232 |
| LMArena Chinese | 1415 | 1225 |
| LMArena French | 1408 | 1268 |
| LMArena German | 1377 | 1248 |
| LMArena Japanese | 1339 | 1176 |
| LMArena Korean | 1346 | 1125 |
| LMArena Russian | 1380 | 1224 |
| LMArena Spanish | 1420 | 1269 |
Instruction Following Claude Haiku 4.5 leads
Claude Haiku 4.5: 71.6 (#144), Magistral Medium: 66.2 (#207)
| Benchmark | Claude Haiku 4.5 | Magistral Medium |
|---|---|---|
| LMArena Instruction Following | 1414 | 1254 |
| IFEval | 80.1% | — |
Long Context Claude Haiku 4.5 leads
Claude Haiku 4.5: 43.6 (#86), Magistral Medium: 39.3 (#178)
| Benchmark | Claude Haiku 4.5 | Magistral Medium |
|---|---|---|
| LMArena Longer Query | 1427 | 1295 |
Writing & Preference Claude Haiku 4.5 leads
Claude Haiku 4.5: 58.1 (#119), Magistral Medium: 46.5 (#214)
| Benchmark | Claude Haiku 4.5 | Magistral Medium |
|---|---|---|
| LMArena Text | 1396 | 1255 |
| LMArena Creative Writing | 1371 | 1245 |
| LMArena Multi-Turn | 1409 | 1275 |
| WildBench | 83.9% | — |
| EQ-Bench 4 | 1064 | — |
Frequently asked questions
Is Claude Haiku 4.5 better than Magistral Medium?
Claude Haiku 4.5 is the stronger model overall, scoring 39.3 to 34.8 on the Noometry Index.
Which is cheaper, Claude Haiku 4.5 or Magistral Medium?
Claude Haiku 4.5 is cheaper. It lists at $1 per million input tokens and $5 per million output tokens; Magistral Medium lists at $2 and $5.
Is Claude Haiku 4.5 or Magistral Medium better for coding?
Claude Haiku 4.5 scores higher on coding benchmarks: 43.9 versus 38.6 in the Noometry coding category.
Which has the bigger context window?
Claude Haiku 4.5 does, with 200K tokens against 128K.
How many benchmarks do Claude Haiku 4.5 and Magistral Medium share?
21 benchmarks have published results for both models. Claude Haiku 4.5 has 53 scored results on Noometry and Magistral Medium has 22.