Model comparison
Claude 3.5 Haiku vs MiniMax-M2.5
MiniMax-M2.5 is the stronger model overall, scoring 38.3 to 29.2 on the Noometry Index.
Last verified . 19 shared benchmarks.
MiniMaxSummary
- They share 19 benchmarks with published results for both. Claude 3.5 Haiku scores higher in 2 categories and MiniMax-M2.5 in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where MiniMax-M2.5 leads 39.2 to 18.7.
- MiniMax-M2.5 has downloadable open weights; the other is API-only.
Side by side
| Claude 3.5 Haiku | MiniMax-M2.5 | |
|---|---|---|
| Provider | Anthropic | MiniMax |
| Noometry Index | 29.2 | 38.3 |
| Released | 2024-10-22 | 2026-02-12 |
| Weights | Proprietary | Open |
| Context window | — | 205K |
| Max output | — | 131K |
| Input $ / M tokens | — | $0.30 |
| Output $ / M tokens | — | $1.20 |
| Results tracked | 49 | 33 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiniMax-M2.5 leads
Claude 3.5 Haiku: 32.9 (#265), MiniMax-M2.5: 48.1 (#58)
| Benchmark | Claude 3.5 Haiku | MiniMax-M2.5 |
|---|---|---|
| LMArena Coding | 1286 | 1381 |
| SWE-bench Verified (bash only) | — | 75.8% |
| Aider Polyglot | 28% | — |
| LMArena WebDev | — | 1387 |
| SWE-bench Multilingual | — | 68.3% |
| SciCode | 27.4% | — |
| WeirdML | 30.7% | — |
| BigCodeBench Instruct | 46.1% | — |
| LiveBench Coding | 51.4% | — |
| BigCodeBench Complete | 59% | — |
| CadEval | 32% | — |
| ALE-Bench | — | 618.17 |
Agentic & Tool Use MiniMax-M2.5 leads
Claude 3.5 Haiku: 28.0 (#95), MiniMax-M2.5: 30.4 (#77)
| Benchmark | Claude 3.5 Haiku | MiniMax-M2.5 |
|---|---|---|
| Terminal-Bench | — | 42.7% |
| BALROG | 19.3% | — |
| Vending-Bench 2 | — | -23.16 |
Reasoning Too close to call
Claude 3.5 Haiku: 17.7 (#290), MiniMax-M2.5: 17.5 (#292)
| Benchmark | Claude 3.5 Haiku | MiniMax-M2.5 |
|---|---|---|
| LMArena Hard Prompts | 1251 | 1372 |
| Epoch Capabilities Index | 127.15 | 146.68 |
| ARC-AGI-2 | — | 4.9% |
| Kagi LLM Benchmark | — | 55.2% |
| NYT Connections (extended) | — | 16.8% |
| ARC-AGI-1 | — | 63.7% |
| CritPt | 0% | — |
| LiveBench Reasoning | 28.1% | — |
| DTBench | 56.7% | — |
| LiveBench Data Analysis | 48.5% | — |
| LiveBench | 43.5% | — |
Math MiniMax-M2.5 leads
Claude 3.5 Haiku: 14.7 (#300), MiniMax-M2.5: 26.9 (#253)
| Benchmark | Claude 3.5 Haiku | MiniMax-M2.5 |
|---|---|---|
| LMArena Math | 1244 | 1378 |
| OTIS Mock AIME 2024-2025 | 4.3% | — |
| ProofBench | — | 4% |
| Omni-MATH | 22.4% | — |
| LiveBench Math | 35.5% | — |
| MATH Level 5 | 46.4% | — |
| FrontierMath (Feb 2025 set) | 0.3% | — |
Knowledge MiniMax-M2.5 leads
Claude 3.5 Haiku: 18.7 (#281), MiniMax-M2.5: 39.2 (#135)
| Benchmark | Claude 3.5 Haiku | MiniMax-M2.5 |
|---|---|---|
| LMArena Expert | 1208 | 1379 |
| GPQA Diamond | 38.1% | — |
| MMLU-Pro | 60.5% | — |
| Confabulations | 36.7% | — |
| Vectara Hallucination Rate | — | 9.1% |
| GPQA (HELM) | 36.3% | — |
| MMLU | 74.3% | — |
Multimodal Not comparable
Claude 3.5 Haiku: 26.8 (#117), MiniMax-M2.5: —
| Benchmark | Claude 3.5 Haiku | MiniMax-M2.5 |
|---|---|---|
| LMArena Vision | 1092 | — |
| GeoBench | 34% | — |
Multilingual MiniMax-M2.5 leads
Claude 3.5 Haiku: 40.0 (#218), MiniMax-M2.5: 47.1 (#152)
| Benchmark | Claude 3.5 Haiku | MiniMax-M2.5 |
|---|---|---|
| LMArena Non-English | 1238 | 1338 |
| LMArena Chinese | 1229 | 1393 |
| LMArena French | 1264 | 1362 |
| LMArena German | 1237 | 1362 |
| LMArena Japanese | 1175 | 1171 |
| LMArena Korean | 1173 | 1232 |
| LMArena Russian | 1253 | 1358 |
| LMArena Spanish | 1261 | 1354 |
Instruction Following MiniMax-M2.5 leads
Claude 3.5 Haiku: 62.9 (#234), MiniMax-M2.5: 71.5 (#148)
| Benchmark | Claude 3.5 Haiku | MiniMax-M2.5 |
|---|---|---|
| LMArena Instruction Following | 1241 | 1353 |
| LiveBench Instruction Following | 61.9% | — |
| IFEval | 79.2% | — |
Long Context Too close to call
Claude 3.5 Haiku: 38.3 (#200), MiniMax-M2.5: 37.5 (#216)
| Benchmark | Claude 3.5 Haiku | MiniMax-M2.5 |
|---|---|---|
| LMArena Longer Query | 1261 | 1366 |
| CL-bench | — | 11.4% |
| CL-bench Life | — | 6.3% |
Writing & Preference MiniMax-M2.5 leads
Claude 3.5 Haiku: 42.7 (#234), MiniMax-M2.5: 53.9 (#153)
| Benchmark | Claude 3.5 Haiku | MiniMax-M2.5 |
|---|---|---|
| LMArena Text | 1255 | 1359 |
| LMArena Creative Writing | 1233 | 1331 |
| EQ-Bench Creative Writing | 1146 | 1361 |
| LMArena Multi-Turn | 1265 | 1364 |
| Short-Story Creative Writing | 73.5% | — |
| WildBench | 76% | — |
| LiveBench Language | 35.4% | — |
Frequently asked questions
Is Claude 3.5 Haiku better than MiniMax-M2.5?
MiniMax-M2.5 is the stronger model overall, scoring 38.3 to 29.2 on the Noometry Index.
Is Claude 3.5 Haiku or MiniMax-M2.5 better for coding?
MiniMax-M2.5 scores higher on coding benchmarks: 48.1 versus 32.9 in the Noometry coding category.
How many benchmarks do Claude 3.5 Haiku and MiniMax-M2.5 share?
19 benchmarks have published results for both models. Claude 3.5 Haiku has 49 scored results on Noometry and MiniMax-M2.5 has 33.