Compare / head-to-head
LongCat Flash ChatvsStep 3.7 Flash
Step 3.7 Flash leads 1 of 1 shared benchmark. Step 3.7 Flash has the larger context window (256K tokens).
Benchmarks from cited public sources; pricing from official pages; status from official provider feeds.
Shared benchmarks
0 – 1
Step 3.7 Flash leads
Cheaper per token
—
list price, input + output
Larger context
Step 3.7 Flash
256K tokens
Provider uptime (30d)
— · —
Meituan LongCat · StepFun
LongCat Flash Chat
Meituan LongCat · released 2025-09-01
text
- Context
- 128K
- Max out
- —
- Input /1M
- —
- Output /1M
- —
- Cached /1M
- —
- Scores
- 31 · 9 core
Step 3.7 Flash
StepFun · released 2026-05-29
textvision
- Context
- 256K
- Max out
- —
- Input /1M
- —
- Output /1M
- —
- Cached /1M
- —
- Scores
- 19 · 6 core
Quality
Benchmark matrix
1 shared · 30 only LongCat Flash Chat · 18 only Step 3.7 Flash| Benchmark | LongCat Flash Chat | Step 3.7 Flash | Δ | Edge |
|---|---|---|---|---|
| Reported by both · 1 | ||||
| SWE-bench Verified | 60.4% ↗ | 76.5% ↗ | -16.1 pt | Step 3.7 Flash |
| Only LongCat Flash Chat reports · 30 | ||||
| GPQA Diamond | 73.23% ↗ | not reported | — | — |
| MMLU | 89.71% ↗ | not reported | — | — |
| MMLU-Pro | 82.68% ↗ | not reported | — | — |
| AIME 2025 | 61.25% ↗ | not reported | — | — |
| LMArena Elo | 1422.9 ↗ | not reported | — | — |
| AceBench | 76.1% ↗ | not reported | — | — |
| AIME 2024 | 70.42% ↗ | not reported | — | — |
| ArenaHard-V2 | 86.5% ↗ | not reported | — | — |
| BeyondAIME | 43% ↗ | not reported | — | — |
| C-Eval | 90.44% ↗ | not reported | — | — |
| CMMLU | 84.34% ↗ | not reported | — | — |
| COLLIE | 57.1% ↗ | not reported | — | — |
| DROP | 79.06% ↗ | not reported | — | — |
| GraphWalks-128k | 51.05% ↗ | not reported | — | — |
| HumanEval+ | 88.41% ↗ | not reported | — | — |
| IFEval | 89.65% ↗ | not reported | — | — |
| LiveCodeBench | 48.02% ↗ | not reported | — | — |
| MATH500 | 96.4% ↗ | not reported | — | — |
| MBPP+ | 79.63% ↗ | not reported | — | — |
| Meeseeks-zh | 43.03% ↗ | not reported | — | — |
| Safety: Criminal | 91.24% ↗ | not reported | — | — |
| Safety: Harmful | 83.98% ↗ | not reported | — | — |
| Safety: Misinformation | 81.72% ↗ | not reported | — | — |
| Safety: Privacy | 93.98% ↗ | not reported | — | — |
| Tau2-Bench (airline) | 58% ↗ | not reported | — | — |
| Tau2-Bench (retail) | 71.27% ↗ | not reported | — | — |
| Tau2-Bench (telecom) | 73.68% ↗ | not reported | — | — |
| TerminalBench | 39.51% ↗ | not reported | — | — |
| VitaBench | 24.3% ↗ | not reported | — | — |
| ZebraLogic | 89.3% ↗ | not reported | — | — |
| Only Step 3.7 Flash reports · 18 | ||||
| AIME 2026 | not reported | 95% ↗matharena ⚠ | — | — |
| AA-LCR | not reported | 63.9% ↗ | — | — |
| BrowseComp | not reported | 75.8% ↗ | — | — |
| ClawEval v1.1 | not reported | 67.1% ↗ | — | — |
| DeepSearchQA Accuracy | not reported | 81.7% ↗ | — | — |
| DeepSearchQA F1 | not reported | 92.8% ↗ | — | — |
| GDPval-Stirrup | not reported | 1415.8 ↗ | — | — |
| GDPval-Stirrup Intelligence Index | not reported | 45.8 ↗ | — | — |
| HLE (with tools, text-only) | not reported | 49.7% ↗ | — | — |
| HLE (with tools) | not reported | 47.2% ↗ | — | — |
| ResearchRubrics | not reported | 71.7% ↗ | — | — |
| SimpleVQA (with tools) | not reported | 79.2% ↗ | — | — |
| SWE-bench Multilingual | not reported | 72.4% ↗ | — | — |
| SWE-bench Pro | not reported | 56.3% ↗ | — | — |
| Terminal-Bench 2.1 | not reported | 59.6% ↗ | — | — |
| Toolathlon | not reported | 49.5% ↗ | — | — |
| V* (with Python) | not reported | 95.3% ↗ | — | — |
| WorldVQA (with visual search) | not reported | 58.1% ↗ | — | — |
Scores tagged "epoch" or "matharena" are independent runs, used only where the lab has not published its own; ⚠ marks rows MathArena flags as released after the competition. Higher is better on every row. Δ is LongCat Flash Chat minus Step 3.7 Flash in the benchmark's own unit. "Not reported" means the lab has not published that figure; it is not a zero. ↗ opens the source.
Specs & pricing
Side by side
Official pricing pages and model cards| Spec | LongCat Flash Chat | Step 3.7 Flash | Edge |
|---|---|---|---|
| Context window | 128K tokens | 256K tokens | Step 3.7 Flash |
| Max output | — | — | — |
| Input price / 1M | — | — | — |
| Output price / 1M | — | — | — |
| Cached input / 1M | — | — | — |
| Input + output / 1M Lower is cheaper. List prices; batch, tool and regional fees excluded. | — | — | — |
| Modalities | text | text · vision | Step 3.7 Flash |
| Released | 2025-09-01 | 2026-05-29 | — |
| Cited benchmark scores | 31 | 19 | — |
Reliability
Provider status
Last 60 days · refreshed daily on this page · live on /statusMore matchups
LongCat Flash Chat vs …
Models sharing the most benchmarksMore matchups
Step 3.7 Flash vs …
Models sharing the most benchmarksBuilt by Respan
Which one wins on your data?
Public benchmarks are a starting point. Run LongCat Flash Chat and Step 3.7 Flash on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.