Compare / head-to-head
GPT-4.1vsLongCat Flash Chat
LongCat Flash Chat leads 3 of 4 shared benchmarks. GPT-4.1 has the larger context window (1.0M tokens).
Benchmarks from cited public sources; pricing from official pages; status from official provider feeds.
Shared benchmarks
1 – 3
LongCat Flash Chat leads
Cheaper per token
—
list price, input + output
Larger context
GPT-4.1
1.0M tokens
Provider uptime (30d)
94.2446% · —
OpenAI · Meituan LongCat
GPT-4.1
OpenAI · released 2025-04-14
textvision
LongCat Flash Chat
Meituan LongCat · released 2025-09-01
text
- Context
- 128K
- Max out
- —
- Input /1M
- —
- Output /1M
- —
- Cached /1M
- —
- Scores
- 31 · 9 core
Quality
Benchmark matrix
4 shared · 5 only GPT-4.1 · 27 only LongCat Flash Chat| Benchmark | GPT-4.1 | LongCat Flash Chat | Δ | Edge |
|---|---|---|---|---|
| Reported by both · 4 | ||||
| SWE-bench Verified | 54.6% ↗ | 60.4% ↗ | -5.8 pt | LongCat Flash Chat |
| GPQA Diamond | 66.3% ↗ | 73.23% ↗ | -6.9 pt | LongCat Flash Chat |
| MMLU | 90.2% ↗ | 89.71% ↗ | +0.5 pt | GPT-4.1 |
| AIME 2024 | 48.1% ↗ | 70.42% ↗ | -22.3 pt | LongCat Flash Chat |
| Only GPT-4.1 reports · 5 | ||||
| FrontierMath Tiers 1-3 v2 (Epoch AI run) | 6% ↗epoch | not reported | — | — |
| OTIS Mock AIME 2024-2025 (Epoch AI run) | 38.3% ↗epoch | not reported | — | — |
| SimpleQA Verified | 31.1% ↗epoch | not reported | — | — |
| SWE-bench Verified (Epoch AI run) | 48.5% ↗epoch | not reported | — | — |
| Video-MME (long, no subtitles) | 72% ↗ | not reported | — | — |
| Only LongCat Flash Chat reports · 27 | ||||
| MMLU-Pro | not reported | 82.68% ↗ | — | — |
| AIME 2025 | not reported | 61.25% ↗ | — | — |
| LMArena Elo | not reported | 1422.9 ↗ | — | — |
| AceBench | not reported | 76.1% ↗ | — | — |
| ArenaHard-V2 | not reported | 86.5% ↗ | — | — |
| BeyondAIME | not reported | 43% ↗ | — | — |
| C-Eval | not reported | 90.44% ↗ | — | — |
| CMMLU | not reported | 84.34% ↗ | — | — |
| COLLIE | not reported | 57.1% ↗ | — | — |
| DROP | not reported | 79.06% ↗ | — | — |
| GraphWalks-128k | not reported | 51.05% ↗ | — | — |
| HumanEval+ | not reported | 88.41% ↗ | — | — |
| IFEval | not reported | 89.65% ↗ | — | — |
| LiveCodeBench | not reported | 48.02% ↗ | — | — |
| MATH500 | not reported | 96.4% ↗ | — | — |
| MBPP+ | not reported | 79.63% ↗ | — | — |
| Meeseeks-zh | not reported | 43.03% ↗ | — | — |
| Safety: Criminal | not reported | 91.24% ↗ | — | — |
| Safety: Harmful | not reported | 83.98% ↗ | — | — |
| Safety: Misinformation | not reported | 81.72% ↗ | — | — |
| Safety: Privacy | not reported | 93.98% ↗ | — | — |
| Tau2-Bench (airline) | not reported | 58% ↗ | — | — |
| Tau2-Bench (retail) | not reported | 71.27% ↗ | — | — |
| Tau2-Bench (telecom) | not reported | 73.68% ↗ | — | — |
| TerminalBench | not reported | 39.51% ↗ | — | — |
| VitaBench | not reported | 24.3% ↗ | — | — |
| ZebraLogic | not reported | 89.3% ↗ | — | — |
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 GPT-4.1 minus LongCat Flash Chat 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 | GPT-4.1 | LongCat Flash Chat | Edge |
|---|---|---|---|
| Context window | 1.0M tokens | 128K tokens | GPT-4.1 |
| Max output | 33K tokens | — | — |
| Input price / 1M | $2 ↗ | — | — |
| Output price / 1M | $8 ↗ | — | — |
| Cached input / 1M | $0.5 ↗ | — | — |
| Input + output / 1M Lower is cheaper. List prices; batch, tool and regional fees excluded. | $10 | — | — |
| Modalities | text · vision | text | GPT-4.1 |
| Released | 2025-04-14 | 2025-09-01 | — |
| Cited benchmark scores | 10 | 31 | — |
Reliability
Provider status
Last 60 days · refreshed daily on this page · live on /statusMore matchups
GPT-4.1 vs …
Models sharing the most benchmarksMore matchups
LongCat Flash Chat vs …
Models sharing the most benchmarksBuilt by Respan
Which one wins on your data?
Public benchmarks are a starting point. Run GPT-4.1 and LongCat Flash Chat on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.