Model comparison
Claude Haiku 4.5 vs MiMo-V2.6-Flash
MiMo-V2.6-Flash is the stronger model overall, scoring 48.5 to 39.5 on the Noometry Index.
Last verified . 17 shared benchmarks.
Summary
- They share 17 benchmarks with published results for both. Claude Haiku 4.5 scores higher in 0 categories and MiMo-V2.6-Flash in 9 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where MiMo-V2.6-Flash leads 36.5 to 15.1.
- The biggest single-benchmark swing is CritPt: 0% for Claude Haiku 4.5 and 12% for MiMo-V2.6-Flash.
- MiMo-V2.6-Flash is cheaper at $0.14 / $0.28 per million input/output tokens, against $1 / $5 for Claude Haiku 4.5.
- MiMo-V2.6-Flash accepts more context: 1.05M tokens versus 200K.
- MiMo-V2.6-Flash has downloadable open weights; the other is API-only.
Side by side
| Claude Haiku 4.5 | MiMo-V2.6-Flash | |
|---|---|---|
| Provider | Anthropic | Xiaomi |
| Noometry Index | 39.5 | 48.5 |
| Released | 2025-10-15 | 2026-09-21 |
| Weights | Proprietary | Open |
| Context window | 200K | 1.05M |
| Max output | 64K | 131K |
| Input $ / M tokens | $1 | $0.14 |
| Output $ / M tokens | $5 | $0.28 |
| Results tracked | 53 | 19 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiMo-V2.6-Flash leads
Claude Haiku 4.5: 44.0 (#78), MiMo-V2.6-Flash: 53.4 (#30)
| Benchmark | Claude Haiku 4.5 | MiMo-V2.6-Flash |
|---|---|---|
| LMArena WebDev | 1330 | 1637 |
| SciCode | 43.3% | 51.3% |
| LMArena Coding | 1453 | 1504 |
| SWE-bench Verified (bash only) | 66.6% | — |
| SWE-bench Multilingual | 64.7% | — |
| WeirdML | 45.4% | — |
| ALE-Bench | 653.48 | — |
Agentic & Tool Use Not comparable
Claude Haiku 4.5: 33.6 (#52), MiMo-V2.6-Flash: —
| Benchmark | Claude Haiku 4.5 | MiMo-V2.6-Flash |
|---|---|---|
| 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 MiMo-V2.6-Flash leads
Claude Haiku 4.5: 15.1 (#320), MiMo-V2.6-Flash: 36.5 (#66)
| Benchmark | Claude Haiku 4.5 | MiMo-V2.6-Flash |
|---|---|---|
| CritPt | 0% | 12% |
| LMArena Hard Prompts | 1420 | 1482 |
| ARC-AGI-2 | 4% | — |
| NYT Connections (extended) | 14.3% | — |
| ARC-AGI-1 | 47.7% | — |
| Chess Puzzles | 8% | — |
| DTBench | 73.6% | — |
| LMCA | 30.9% | — |
| Epoch Capabilities Index | 142.41 | — |
| ForecastBench | 61.4 | — |
Math MiMo-V2.6-Flash leads
Claude Haiku 4.5: 44.9 (#78), MiMo-V2.6-Flash: 51.9 (#52)
| Benchmark | Claude Haiku 4.5 | MiMo-V2.6-Flash |
|---|---|---|
| LMArena Math | 1396 | 1468 |
| OTIS Mock AIME 2024-2025 | 66.7% | — |
| ProofBench | — | 63% |
| Omni-MATH | 56.1% | — |
| MATH Level 5 | 96.4% | — |
| FrontierMath (Feb 2025 set) | 5.9% | — |
| FrontierMath Tier 4 (v1) | 2.1% | — |
Knowledge MiMo-V2.6-Flash leads
Claude Haiku 4.5: 37.7 (#153), MiMo-V2.6-Flash: 42.2 (#99)
| Benchmark | Claude Haiku 4.5 | MiMo-V2.6-Flash |
|---|---|---|
| LMArena Expert | 1442 | 1501 |
| GPQA Diamond | 71.2% | — |
| SimpleQA Verified | 13.2% | — |
| MMLU-Pro | 77.7% | — |
| Vectara Hallucination Rate | 9.8% | — |
| GPQA (HELM) | 60.5% | — |
Multimodal MiMo-V2.6-Flash leads
Claude Haiku 4.5: 26.8 (#118), MiMo-V2.6-Flash: 40.5 (#47)
| Benchmark | Claude Haiku 4.5 | MiMo-V2.6-Flash |
|---|---|---|
| LMArena Vision | — | 1259 |
| Blueprint-Bench 2 | 0% | — |
| LMArena Document | 1420 | — |
Multilingual MiMo-V2.6-Flash leads
Claude Haiku 4.5: 49.9 (#129), MiMo-V2.6-Flash: 54.0 (#51)
| Benchmark | Claude Haiku 4.5 | MiMo-V2.6-Flash |
|---|---|---|
| LMArena Non-English | 1377 | 1434 |
| LMArena Chinese | 1417 | 1511 |
| LMArena French | 1408 | 1475 |
| LMArena Russian | 1381 | 1409 |
| LMArena Spanish | 1420 | 1456 |
| LMArena German | 1375 | — |
| LMArena Japanese | 1339 | — |
| LMArena Korean | 1347 | — |
Instruction Following MiMo-V2.6-Flash leads
Claude Haiku 4.5: 71.4 (#149), MiMo-V2.6-Flash: 76.8 (#35)
| Benchmark | Claude Haiku 4.5 | MiMo-V2.6-Flash |
|---|---|---|
| LMArena Instruction Following | 1414 | 1463 |
| IFEval | 80.1% | — |
Long Context MiMo-V2.6-Flash leads
Claude Haiku 4.5: 43.6 (#92), MiMo-V2.6-Flash: 44.8 (#57)
| Benchmark | Claude Haiku 4.5 | MiMo-V2.6-Flash |
|---|---|---|
| LMArena Longer Query | 1427 | 1463 |
Writing & Preference MiMo-V2.6-Flash leads
Claude Haiku 4.5: 57.9 (#123), MiMo-V2.6-Flash: 63.1 (#67)
| Benchmark | Claude Haiku 4.5 | MiMo-V2.6-Flash |
|---|---|---|
| LMArena Text | 1396 | 1455 |
| LMArena Creative Writing | 1372 | 1400 |
| LMArena Multi-Turn | 1409 | 1451 |
| WildBench | 83.9% | — |
| EQ-Bench 4 | 1064 | — |
Frequently asked questions
Is Claude Haiku 4.5 better than MiMo-V2.6-Flash?
MiMo-V2.6-Flash is the stronger model overall, scoring 48.5 to 39.5 on the Noometry Index.
Which is cheaper, Claude Haiku 4.5 or MiMo-V2.6-Flash?
MiMo-V2.6-Flash is cheaper. It lists at $0.14 per million input tokens and $0.28 per million output tokens; Claude Haiku 4.5 lists at $1 and $5.
Is Claude Haiku 4.5 or MiMo-V2.6-Flash better for coding?
MiMo-V2.6-Flash scores higher on coding benchmarks: 53.4 versus 44.0 in the Noometry coding category.
Which has the bigger context window?
MiMo-V2.6-Flash does, with 1.05M tokens against 200K.
How many benchmarks do Claude Haiku 4.5 and MiMo-V2.6-Flash share?
17 benchmarks have published results for both models. Claude Haiku 4.5 has 53 scored results on Noometry and MiMo-V2.6-Flash has 19.