Model comparison
Claude Haiku 4.5 vs Longcat Flash Chat
Longcat Flash Chat is the stronger model overall, scoring 42.1 to 39.5 on the Noometry Index.
Last verified . 18 shared benchmarks.
Summary
- They share 18 benchmarks with published results for both. Claude Haiku 4.5 scores higher in 3 categories and Longcat Flash Chat in 5 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in math, where Claude Haiku 4.5 leads 44.9 to 39.4.
- Longcat Flash Chat has downloadable open weights; the other is API-only.
Side by side
| Claude Haiku 4.5 | Longcat Flash Chat | |
|---|---|---|
| Provider | Anthropic | Meituan |
| Noometry Index | 39.5 | 42.1 |
| Released | 2025-10-15 | — |
| Weights | Proprietary | Open |
| Context window | 200K | — |
| Max output | 64K | — |
| Input $ / M tokens | $1 | — |
| Output $ / M tokens | $5 | — |
| Results tracked | 53 | 19 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Claude Haiku 4.5: 44.0 (#78), Longcat Flash Chat: 43.5 (#87)
| Benchmark | Claude Haiku 4.5 | Longcat Flash Chat |
|---|---|---|
| LMArena Coding | 1453 | 1471 |
| SWE-bench Verified (bash only) | 66.6% | — |
| LMArena WebDev | 1330 | — |
| SWE-bench Multilingual | 64.7% | — |
| SciCode | 43.3% | — |
| WeirdML | 45.4% | — |
| ALE-Bench | 653.48 | — |
Agentic & Tool Use Not comparable
Claude Haiku 4.5: 33.6 (#52), Longcat Flash Chat: —
| Benchmark | Claude Haiku 4.5 | Longcat Flash Chat |
|---|---|---|
| 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 Longcat Flash Chat leads
Claude Haiku 4.5: 15.1 (#320), Longcat Flash Chat: 19.0 (#272)
| Benchmark | Claude Haiku 4.5 | Longcat Flash Chat |
|---|---|---|
| NYT Connections (extended) | 14.3% | 17.7% |
| LMArena Hard Prompts | 1420 | 1440 |
| ARC-AGI-2 | 4% | — |
| Kagi LLM Benchmark | — | 43.9% |
| ARC-AGI-1 | 47.7% | — |
| CritPt | 0% | — |
| Chess Puzzles | 8% | — |
| DTBench | 73.6% | — |
| LMCA | 30.9% | — |
| Epoch Capabilities Index | 142.41 | — |
| ForecastBench | 61.4 | — |
Math Claude Haiku 4.5 leads
Claude Haiku 4.5: 44.9 (#78), Longcat Flash Chat: 39.4 (#107)
| Benchmark | Claude Haiku 4.5 | Longcat Flash Chat |
|---|---|---|
| LMArena Math | 1396 | 1442 |
| 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 Longcat Flash Chat leads
Claude Haiku 4.5: 37.7 (#153), Longcat Flash Chat: 40.6 (#116)
| Benchmark | Claude Haiku 4.5 | Longcat Flash Chat |
|---|---|---|
| LMArena Expert | 1442 | 1454 |
| 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: 26.8 (#118), Longcat Flash Chat: —
| Benchmark | Claude Haiku 4.5 | Longcat Flash Chat |
|---|---|---|
| Blueprint-Bench 2 | 0% | — |
| LMArena Document | 1420 | — |
Multilingual Longcat Flash Chat leads
Claude Haiku 4.5: 49.9 (#129), Longcat Flash Chat: 51.9 (#101)
| Benchmark | Claude Haiku 4.5 | Longcat Flash Chat |
|---|---|---|
| LMArena Non-English | 1377 | 1404 |
| LMArena Chinese | 1417 | 1465 |
| LMArena French | 1408 | 1456 |
| LMArena German | 1375 | 1408 |
| LMArena Japanese | 1339 | 1373 |
| LMArena Korean | 1347 | 1371 |
| LMArena Russian | 1381 | 1395 |
| LMArena Spanish | 1420 | 1445 |
Instruction Following Longcat Flash Chat leads
Claude Haiku 4.5: 71.4 (#149), Longcat Flash Chat: 74.4 (#96)
| Benchmark | Claude Haiku 4.5 | Longcat Flash Chat |
|---|---|---|
| LMArena Instruction Following | 1414 | 1411 |
| IFEval | 80.1% | — |
Long Context Too close to call
Claude Haiku 4.5: 43.6 (#92), Longcat Flash Chat: 43.5 (#93)
| Benchmark | Claude Haiku 4.5 | Longcat Flash Chat |
|---|---|---|
| LMArena Longer Query | 1427 | 1425 |
Writing & Preference Longcat Flash Chat leads
Claude Haiku 4.5: 57.9 (#123), Longcat Flash Chat: 61.0 (#91)
| Benchmark | Claude Haiku 4.5 | Longcat Flash Chat |
|---|---|---|
| LMArena Text | 1396 | 1427 |
| LMArena Creative Writing | 1372 | 1388 |
| LMArena Multi-Turn | 1409 | 1418 |
| WildBench | 83.9% | — |
| EQ-Bench 4 | 1064 | — |
Frequently asked questions
Is Claude Haiku 4.5 better than Longcat Flash Chat?
Longcat Flash Chat is the stronger model overall, scoring 42.1 to 39.5 on the Noometry Index.
Is Claude Haiku 4.5 or Longcat Flash Chat better for coding?
They score almost the same on coding (44.0 vs 43.5); test both on your own repository before choosing.
How many benchmarks do Claude Haiku 4.5 and Longcat Flash Chat share?
18 benchmarks have published results for both models. Claude Haiku 4.5 has 53 scored results on Noometry and Longcat Flash Chat has 19.