BlogLLM Benchmark Scores as Published, Side by Side
DeepSeek-V4-Flash-0731: Benchmark Scores as Published
Every result the catalog holds for DeepSeek-V4-Flash-0731: 43 tests in 13 areas, from 6 pages. 18 printed by DeepSeek itself, the rest by the company named beside each number. Each number is as printed; nothing is ranked or rescored.
Developer DeepSeekInput TextOutput TextWeights Open (MIT)Data version 2026103001, as of 2026-10-30
Knowledge Work
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| AutomationBench | 25.1% | DeepSeek, DeepSeek-V4-Flash-0731 model cardchecked 2026-10-15; printed on 3 more pages | - |
| GDPval-AA v2 | 1382 | NVIDIA, NVIDIA Nemotron 3.5 Super VL 120B-A12B model cardchecked 2026-10-19 | - |
| JobBench | 41.3 | Alibaba, Qwen3.8-Flash-Next model cardchecked 2026-10-15 | - |
| CoWorkBench | 45.1 | Alibaba, Qwen3.8-Flash-Next model cardchecked 2026-10-15 | - |
Agentic Coding
Science and Math
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| GPQA Diamond | 89.9% | DeepSeek, DeepSeek-V4.1-Flash model cardchecked 2026-10-15; printed on 2 more pages | Effort: max |
| SciCode | 49.3% | NVIDIA, NVIDIA Nemotron 3.5 Super VL 120B-A12B model cardchecked 2026-10-19 | - |
| CritPt | 12.6% | NVIDIA, NVIDIA Nemotron 3.5 Super VL 120B-A12B model cardchecked 2026-10-19 | - |
| MathArena Apex Shortlist | 88.7% | NVIDIA, NVIDIA Nemotron 3.5 Super VL 120B-A12B model cardchecked 2026-10-19 | - |
| MathArena Apex | 58.6% | DeepSeek, DeepSeek-V4.1-Flash model cardchecked 2026-10-15 | Effort: max |
Long Context
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| AA-LCR | 79.7% | NVIDIA, NVIDIA Nemotron 3.5 Super VL 120B-A12B model cardchecked 2026-10-19 | - |
| GraphWalks (variant not stated) | 65.4% | NVIDIA, NVIDIA Nemotron 3.5 Super VL 120B-A12B model cardchecked 2026-10-19 | - |
Multimodal Understanding
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| GDP.pdf | 10.8% | NVIDIA, NVIDIA Nemotron 3.5 Super VL 120B-A12B model cardchecked 2026-10-19 | - |
Cybersecurity
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| CyberGym | 76.7% | DeepSeek, DeepSeek-V4-Flash-0731 model cardchecked 2026-10-15; printed on 2 more pages | - |
| ExploitGym | 1.8% | DeepSeek, DeepSeek-V4.1-Flash model cardchecked 2026-10-15 | Effort: max |
| SEC-Bench Pro | 30.9% | DeepSeek, DeepSeek-V4.1-Flash model cardchecked 2026-10-15 | Effort: max |
General Knowledge and Reasoning
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| Humanity's Last Exam (no tools) | 37.8% | DeepSeek, DeepSeek-V4.1-Flash model cardchecked 2026-10-15; printed on 3 more pages | Effort: max; Dataset revision: text-only subset of HLE (dagger on the card) |
| Humanity's Last Exam (with tools) | 51.5% | DeepSeek, DeepSeek-V4.1-Flash model cardchecked 2026-10-15; printed on 1 more page | Effort: max; Tools: enabled; exact tools in source |
| AA-Omniscience Accuracy | 45% | NVIDIA, NVIDIA Nemotron 3.5 Super VL 120B-A12B model cardchecked 2026-10-19 | - |
| AA-Omniscience Index | -7.8 | NVIDIA, NVIDIA Nemotron 3.5 Super VL 120B-A12B model cardchecked 2026-10-19 | - |
| AA-Omniscience Hallucination Ratelower is better | 95.9% | NVIDIA, NVIDIA Nemotron 3.5 Super VL 120B-A12B model cardchecked 2026-10-19 | - |
Code Generation
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| LiveCodeBench v6 | 90.6% | Alibaba, Qwen3.8-Flash-Next model cardchecked 2026-10-15; printed on 1 more page | - |
| Codeforces rating | 3289 | DeepSeek, DeepSeek-V4.1-Flash model cardchecked 2026-10-15 | Effort: max |
Tool Use and Workflows
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| τ³-bench Banking | 38.6% | NVIDIA, NVIDIA Nemotron 3.5 Super VL 120B-A12B model cardchecked 2026-10-19 | - |
| τ²-bench Telecom | 98.2% | NVIDIA, NVIDIA Nemotron 3.5 Super VL 120B-A12B model cardchecked 2026-10-19 | - |
| Agents' Last Exam (pass rate) | 25.2% | DeepSeek, DeepSeek-V4-Flash-0731 model cardchecked 2026-10-15; printed on 3 more pages | - |
| Toolathlon Verified | 70.3% | DeepSeek, DeepSeek-V4-Flash-0731 model cardchecked 2026-10-15; printed on 2 more pages | - |
| τ²-bench Retail | 73.8% | NVIDIA, NVIDIA Nemotron 3.5 Super VL 120B-A12B model cardchecked 2026-10-19 | - |
| τ²-bench Airline | 83.5% | NVIDIA, NVIDIA Nemotron 3.5 Super VL 120B-A12B model cardchecked 2026-10-19 | - |
Web Search and Research
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| BrowseComp | 84.2% | NVIDIA, NVIDIA Nemotron 3.5 Super VL 120B-A12B model cardchecked 2026-10-19 | - |
Instruction Following
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| IFBench | 79.2 | Alibaba, Qwen3.8-Flash-Next model cardchecked 2026-10-15; printed on 1 more page | - |
Multilingual
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| MMLU-ProX | 85.5% | NVIDIA, NVIDIA Nemotron 3.5 Super VL 120B-A12B model cardchecked 2026-10-19 | - |
| WMT24++ (XCOMET-XXL) | 85.5 | NVIDIA, NVIDIA Nemotron 3.5 Super VL 120B-A12B model cardchecked 2026-10-19 | - |
Writing and Conversation
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| LMArena v3 proxy | 49.8 | NVIDIA, NVIDIA Nemotron 3.5 Super VL 120B-A12B model cardchecked 2026-10-19 | - |
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 |
|---|---|---|---|
| Cost per taskVals AI, USD, lower is better | $0.91 | Vals AI, Vibe Code Bench v1.1 leaderboardchecked 2026-10-27 | Harness: OpenHands |
More from DeepSeek
- DeepSeek-V4.1-Flash-1017
- DeepSeek-V4.1-Flash
- 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-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.