BlogLLM Benchmark Scores as Published, Side by Side
DeepSeek-V4.1-Flash: Benchmark Scores as Published
Every result the catalog holds for DeepSeek-V4.1-Flash: 33 tests in 10 areas, from 8 pages. 20 printed by DeepSeek itself, the rest by the company named beside each number. Each number is as printed; nothing is ranked or rescored.
Developer DeepSeekReleased 2026-09-10Context window 1MInput Text, imageOutput TextWeights Open (MIT)Data version 2026103001, as of 2026-10-30
Knowledge Work
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| AutomationBench | 54.8% | DeepSeek, DeepSeek-V4.1-Flash model cardchecked 2026-10-15; printed on 2 more pages | Effort: max; Harness: official scaffold |
| Apex Bench v1.1 | 64.6% | DeepSeek, DeepSeek-V4.1-Flash-1017 model cardchecked 2026-10-18 | - |
Agentic Coding
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| Terminal-Bench 2.1 | 84.1% | DeepSeek, DeepSeek-V4.1-Flash model cardchecked 2026-10-15 | Effort: max; Harness: Codex; Attempt budget: N=3 samples per task; Context: 1M |
| 90.3% | DeepSeek, DeepSeek-V4.1-Flash model cardchecked 2026-10-15 | Effort: max; Harness: mini-SWE; Attempt budget: N=3 samples per task; Context: 1M | |
| 85.8% | DeepSeek, DeepSeek-V4.1-Flash model cardchecked 2026-10-15 | Effort: max; Harness: DeepSeek Harness (DSH) Standard; Attempt budget: N=3 samples per task; Context: 1M | |
| 90.6% | DeepSeek, DeepSeek-V4.1-Flash model cardchecked 2026-10-15 | Effort: max; Harness: DeepSeek Harness (DSH) Minimal; Attempt budget: N=3 samples per task (scaffold table); Context: 1M | |
| 85% | DeepSeek, DeepSeek-V4.1-Flash model cardchecked 2026-10-15 | Effort: max; Harness: OpenCode; Attempt budget: N=3 samples per task; Context: 1M | |
| 88% | DeepSeek, DeepSeek-V4.1-Flash model cardchecked 2026-10-15 | Effort: max; Harness: Claude Code; Attempt budget: N=3 samples per task; Context: 1M | |
| 86.1% | DeepSeek, DeepSeek-V4.1-Flash model cardchecked 2026-10-15 | Effort: max; Harness: Pi; Attempt budget: N=3 samples per task; Context: 1M | |
| 85.8% | DeepSeek, DeepSeek-V4.1-Flash model cardchecked 2026-10-15 | Effort: max; Harness: DeepSeek Harness (DSH) PTC; Attempt budget: N=3 samples per task; Context: 1M | |
| DeepSWE v1.1 | 69.8% | DeepSeek, DeepSeek-V4.1-Flash model cardchecked 2026-10-15; printed on 2 more pages | Effort: max; Harness: Claude Code; Attempt budget: N=8 samples per task; Context: 1M |
| 74.2% | DeepSeek, DeepSeek-V4.1-Flash model cardchecked 2026-10-15 | Effort: max; Harness: mini-SWE; Attempt budget: N=8 samples per task (scaffold table); Context: 1M | |
| 72.6% | DeepSeek, DeepSeek-V4.1-Flash model cardchecked 2026-10-15 | Effort: max; Harness: DeepSeek Harness (DSH) Minimal; Attempt budget: N=8 samples per task; Context: 1M | |
| 65.6% | DeepSeek, DeepSeek-V4.1-Flash model cardchecked 2026-10-15 | Effort: max; Harness: Codex; Attempt budget: N=8 samples per task; Context: 1M | |
| 66.2% | DeepSeek, DeepSeek-V4.1-Flash model cardchecked 2026-10-15 | Effort: max; Harness: Pi; Attempt budget: N=8 samples per task; Context: 1M | |
| 70.5% | DeepSeek, DeepSeek-V4.1-Flash model cardchecked 2026-10-15 | Effort: max; Harness: DeepSeek Harness (DSH) Standard; Attempt budget: N=8 samples per task; Context: 1M | |
| 67.6% | DeepSeek, DeepSeek-V4.1-Flash model cardchecked 2026-10-15 | Effort: max; Harness: DeepSeek Harness (DSH) PTC; Attempt budget: N=8 samples per task; Context: 1M | |
| 65.5% | DeepSeek, DeepSeek-V4.1-Flash model cardchecked 2026-10-15 | Effort: max; Harness: OpenCode; Attempt budget: N=8 samples per task; Context: 1M | |
| Terminal-Bench 4.0 | 31.2% | DeepSeek, DeepSeek-V4.1-Flash model cardchecked 2026-10-15; printed on 2 more pages | Effort: max; Harness: DeepSeek Harness (DSH) Minimal; Context: 1M |
| NL2Repo-Bench | 64 | DeepSeek, DeepSeek-V4.1-Flash model cardchecked 2026-10-15; printed on 2 more pages | Effort: max; Harness: DeepSeek Harness (DSH) Minimal; Context: 1M |
| ProgramBench Almost@1 | 20.3% | DeepSeek, DeepSeek-V4.1-Flash model cardchecked 2026-10-15; printed on 1 more page | Effort: max; Harness: DeepSeek Harness (DSH) Minimal; Context: 1M |
| Terminal-Bench 3.0 | 30% | DeepSeek, DeepSeek-V4.1-Flash model cardchecked 2026-10-15 | Effort: max; Harness: DeepSeek Harness (DSH) Minimal; Context: 1M |
ML Engineering
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| PostTrainBench v1.1 | 30.5% | MiniMax, MiniMax-M3.1-Flash model cardchecked 2026-10-25 | Dataset revision: v1.1 |
Science and Math
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| GPQA Diamond | 90.9% | DeepSeek, DeepSeek-V4.1-Flash model cardchecked 2026-10-15 | Effort: max |
| MathArena Apex | 65.6% | DeepSeek, DeepSeek-V4.1-Flash model cardchecked 2026-10-15 | Effort: max |
| SciCode-Verified | 77.9% | Mistral AI, Mistral Large 4 (preview)checked 2026-10-15 | Attempt budget: pass@1 (n=6) |
Computer Use
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| OSWorld 2.0 | 54.3% | MiniMax, MiniMax-M3.1-Flash model cardchecked 2026-10-25 | Dataset revision: 0808 Full release |
Multimodal Understanding
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| CharXiv Reasoning (no tools) | 69% | MiniMax, MiniMax-M3.1-Flash model cardchecked 2026-10-25 | Tools: none |
| GDP.pdf | 12.8% | MiniMax, MiniMax-M3.1-Flash model cardchecked 2026-10-25; printed on 1 more page | - |
| BabyVision (with tools) | 89.6% | DeepSeek, DeepSeek-V4.1-Flash model cardchecked 2026-10-15; printed on 2 more pages | Effort: max; Harness: Claude Code; Tools: enabled; exact tools in source; Context: 512k |
| Chartography (with tools) | 78.9% | DeepSeek, DeepSeek-V4.1-Flash model cardchecked 2026-10-15; printed on 1 more page | Effort: max; Harness: Claude Code; Tools: enabled; exact tools in source; Context: 512k |
| ZeroBench (with tools, pass@5) | 49% | DeepSeek, DeepSeek-V4.1-Flash model cardchecked 2026-10-15; printed on 1 more page | Effort: max; Harness: Claude Code; Tools: enabled; exact tools in source; Context: 512k |
| ChartQA Pro | 59.9% | Mistral AI, Mistral Large 4 (preview)checked 2026-10-15 | - |
| Dense200 (bbox) | 3.3% | Mistral AI, Mistral Large 4 (preview)checked 2026-10-15 | - |
Cybersecurity
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| CyberGym | 88.1% | DeepSeek, DeepSeek-V4.1-Flash model cardchecked 2026-10-15 | Effort: max |
| ExploitGym | 15.3% | DeepSeek, DeepSeek-V4.1-Flash model cardchecked 2026-10-15 | Effort: max |
| SEC-Bench Pro | 62.8% | DeepSeek, DeepSeek-V4.1-Flash model cardchecked 2026-10-15; printed on 1 more page | Effort: max; Harness: Claude Code |
| CWE-bench v1 | 55% | Google, Gemini 4 Carbon: our next frontier modelchecked 2026-10-29 | Harness: opencode |
| Artificial Analysis Cyber Index (successes) | 41 | Mistral AI, Mistral Large 4 (preview)checked 2026-10-15 | - |
| CyberGym-E2E | 23% | Mistral AI, Mistral Large 4 (preview)checked 2026-10-15 | - |
| xdev-bench-hard, problems solved (pass@3) | 85.7% | Moonshot AI, Introducing Kimi K3.1 Prochecked 2026-10-24 | Harness: Claude Code; Attempt budget: pass@3 |
| xdev-bench-hard, average success rate | 57.1% | Moonshot AI, Introducing Kimi K3.1 Prochecked 2026-10-24 | Harness: Claude Code; Attempt budget: pass@3 |
General Knowledge and Reasoning
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| Humanity's Last Exam (no tools) | 39.1% | DeepSeek, DeepSeek-V4.1-Flash model cardchecked 2026-10-15; printed on 2 more pages | Effort: max; Dataset revision: text-only subset of HLE (dagger on the card) |
| 36.8% | DeepSeek, DeepSeek-V4.1-Flash model cardchecked 2026-10-15 | Effort: max | |
| Humanity's Last Exam (with tools) | 63.9% | DeepSeek, DeepSeek-V4.1-Flash model cardchecked 2026-10-15 | Effort: max; Tools: enabled; exact tools in source |
Code Generation
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| Codeforces rating | 3471 | DeepSeek, DeepSeek-V4.1-Flash model cardchecked 2026-10-15 | Effort: max |
Tool Use and Workflows
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| Agents' Last Exam (pass rate) | 31.8% | DeepSeek, DeepSeek-V4.1-Flash model cardchecked 2026-10-15; printed on 1 more page | Effort: max; Harness: official scaffold |
| BankerToolBench | 73.7% | MiniMax, MiniMax-M3.1-Flash model cardchecked 2026-10-25 | - |
Price
API list prices in US dollars per one million tokens, as printed on the developer's pricing page on the day checked. Cost per task is measured by Vals AI.
| Price | Value | Printed by | Setup as printed |
|---|---|---|---|
| Input | $0.3 | DeepSeek, DeepSeek API pricingchecked 2026-10-15 | - |
| Cached input | $0.006 | DeepSeek, DeepSeek API pricingchecked 2026-10-15 | - |
| Output | $1.2 | DeepSeek, DeepSeek API pricingchecked 2026-10-15 | - |
| Input, off-peak hours | $0.15 | DeepSeek, DeepSeek API pricingchecked 2026-10-15 | - |
| Cached input, off-peak hours | $0.003 | DeepSeek, DeepSeek API pricingchecked 2026-10-15 | - |
| Output, off-peak hours | $0.6 | DeepSeek, DeepSeek API pricingchecked 2026-10-15 | - |
| Cost per taskVals AI, USD, lower is better | $0.41 | Vals AI, Vibe Code Bench v1.1 leaderboardchecked 2026-10-27 | Harness: OpenHands |
More from DeepSeek
- DeepSeek-V4.1-Flash-1017
- DeepSeek-V4-Flash (Preview)
- DeepSeek-V4-Flash-Base
- DeepSeek-V4-Pro (Preview)
- DeepSeek-V4-Pro-Base
- DeepSeek-V3.2
- DeepSeek-V3.2-Base
- DeepSeek-V3.2-Speciale
- DeepSeek-V3.2-Exp
- DeepSeek-V3.1-Terminus
- DeepSeek-V3.1
- DeepSeek-R1-0528
- DeepSeek-R1-0528-Qwen3-8B
- DeepSeek-V3-0324
- DeepSeek-R1
- DeepSeek-R1-Distill-Llama-70B
- DeepSeek-R1-Distill-Llama-8B
- DeepSeek-R1-Distill-Qwen-1.5B
- DeepSeek-R1-Distill-Qwen-14B
- DeepSeek-R1-Distill-Qwen-32B
- DeepSeek-R1-Distill-Qwen-7B
- DeepSeek-V3
- DeepSeek-V4-Flash-0731
- DeepSeek-V4-Pro-0813
- DeepSeek-V4-Vision-Exp
Every number here is read from the same catalog file as the benchmark table, data version 2026103001. Where one page printed the model under several setups, each value is listed. The catalog is public in armanobosyan/sugra-llm-benchmarks; a wrong number can be reported from the table, with Report an error under the value, or as an issue in that repository.