DeepSeek-V4.1-FlashvsClaude Opus 5
Across 13 shared benchmarks, Claude Opus 5 leads overall: DeepSeek-V4.1-Flash wins 5, Claude Opus 5 wins 8, with 0 ties and an average score difference of -5.07.
DeepSeek-V4.1-Flash
DeepSeek-AI · 2026-09-10 · Multimodal model
Claude Opus 5
Anthropic · 2026-07-24 · Reasoning model
DeepSeek-V4.1-Flash5 wins(38%)(62%)8 winsClaude Opus 5
Benchmark scores
Grouped by capability, sorted by largest gap within each. 13 shared benchmarks.
AI Agent - Tool Usage
Claude Opus 5 2/3| Benchmark | DeepSeek-V4.1-Flash | Claude Opus 5 | Diff |
|---|---|---|---|
| Terminal-Bench 4.0 | 31.207 / 16Max (With Tools) | 51.803 / 16Max (With Tools) | -20.60 |
| Terminal-Bench 3.0 | 304 / 11Max (With Tools) | 43.301 / 11Max (With Tools) | -13.30 |
| Terminal-Bench 2.1 | 90.601 / 53Max (With Tools) | 89.103 / 53Max (With Tools) | +1.50 |
Coding and Software Engineer
Claude Opus 5 2/3| Benchmark | DeepSeek-V4.1-Flash | Claude Opus 5 | Diff |
|---|---|---|---|
| Program Bench | 20.308 / 11Max (With Tools) | 375 / 11Max (With Tools) | -16.70 |
| NL2Repo-Bench | 65.402 / 16Max (With Tools) | 75.301 / 16Max (With Tools) | -9.90 |
| DeepSWE | 74.202 / 38Max (With Tools) | 744 / 38Max (With Tools) | +0.20 |
Multimodal Understanding
Claude Opus 5 3/3| Benchmark | DeepSeek-V4.1-Flash | Claude Opus 5 | Diff |
|---|---|---|---|
| Chartography | 78.904 / 8Max (With Tools) | 842 / 8Max (With Tools) | -5.10 |
| BabyVision | 89.603 / 9Max (With Tools) | 94.101 / 9Max (With Tools) | -4.50 |
| ZeroBench Main | 493 / 6Max (With Tools) | 522 / 6Max (With Tools) | -3 |
Agent Level Benchmark
DeepSeek-V4.1-Flash 1/1| Benchmark | DeepSeek-V4.1-Flash | Claude Opus 5 | Diff |
|---|---|---|---|
| Agents' Last Exam | 31.806 / 19Max (With Tools) | 28.607 / 19Max (With Tools) | +3.20 |
General Evaluation
Claude Opus 5 1/1| Benchmark | DeepSeek-V4.1-Flash | Claude Opus 5 | Diff |
|---|---|---|---|
| GPQA Diamond | 90.9039 / 274Max (No Tools) | 93.4018 / 274Max (No Tools) | -2.50 |
General Knowledge
DeepSeek-V4.1-Flash 1/1| Benchmark | DeepSeek-V4.1-Flash | Claude Opus 5 | Diff |
|---|---|---|---|
| HLE | 63.903 / 197Max (With Tools) | 63.604 / 197Max (With Tools) | +0.30 |
Productivity Knowledge
DeepSeek-V4.1-Flash 1/1| Benchmark | DeepSeek-V4.1-Flash | Claude Opus 5 | Diff |
|---|---|---|---|
| AutomationBench | 54.801 / 17Max (With Tools) | 50.303 / 17Max (With Tools) | +4.50 |
Specs
| Field | DeepSeek-V4.1-Flash | Claude Opus 5 |
|---|---|---|
| Publisher | DeepSeek-AI | Anthropic |
| Release date | 2026-09-10 | 2026-07-24 |
| Model type | Multimodal model | Reasoning model |
| Architecture | MoE | Dense |
| Parameters | 552B | Not available |
| Context length | 1M | 1M |
| Max output | 384K | 128K |
API pricing
Prices use DataLearner records when available; missing fields are not inferred.
| Item | DeepSeek-V4.1-Flash | Claude Opus 5 |
|---|---|---|
| Text input | ¥1 / 1M tokens | $5 / 1M tokens |
| Text output | ¥4 / 1M tokens | $25 / 1M tokens |
| Cache read | ¥0.02 / 1M tokens | $0.5 / 1M tokens |
| Cache write | Not public | $6.25 / 1M tokens |
Summary
- DeepSeek-V4.1-Flashleads in:Agent Level Benchmark (1/1), General Knowledge (1/1), Productivity Knowledge (1/1)
- Claude Opus 5leads in:AI Agent - Tool Usage (2/3), Coding and Software Engineer (2/3), Multimodal Understanding (3/3), General Evaluation (1/1)
On average across the 13 shared benchmarks, Claude Opus 5 scores 5.07 higher.
Largest single-benchmark gap: Terminal-Bench 4.0 — DeepSeek-V4.1-Flash 31.20 vs Claude Opus 5 51.80 (-20.60).
Page generated from structured model, pricing and benchmark records. No real-time LLM is used to write the prose.