Agnes 3.0 Flash vs DeepSeek V4 Pro
Agnes 3.0 Flash 
DeepSeek V4 Pro Verdict
- DeepSeek V4 Pro (max) leads on quality: 64.2 vs 62.3.
- Agnes 3.0 Flash is stronger in agents & tools, knowledge, long context, reasoning.
- DeepSeek V4 Pro (max) is stronger in composite, coding, instruction following, maths.
- Agnes 3.0 Flash is 7.3× cheaper ($0.075 vs $0.544 per 1M blended).
| Metric | Agnes 3.0 Flash | DeepSeek V4 Pro (max) |
|---|---|---|
| BenchLeader Index | 62.3 | 64.2 |
| Agents & tools score | 76.8 | 70.2 |
| Composite score | 74.0 | 75.0 |
| Knowledge score | 59.1 | 58.1 |
| Long context score | 67.0 | 66.6 |
| Reasoning score | 71.1 | 70.9 |
| Coding score | – | 58.8 |
| Instruction following score | – | 74.3 |
| Maths score | – | 53.7 |
| Blended price $/M | $0.075 | $0.544 |
| Output speed | – | 81 tok/s |
| Time to first answer | – | 55.6 s |
| Context window | 1M | 1M |
| GPQA Diamond | – | 89.7% |
| FrontierMath Tiers 1–3 | – | 45.3% |
| FrontierMath Tier 4 | – | 2.4% |
| OTIS Mock AIME | – | 96.7% |
| SWE-bench Verified (Epoch) | – | 77.6% |
| SimpleQA Verified | – | 47.0% |
| SciCode | – | 50.0% |
| WeirdML | – | 48.9% |
| ProofBench | – | 16.0% |
| AA Intelligence Index | 35.5 | 36.3 |
| IFBench | – | 76.5% |
| AA-LCR | 81.0% | 80.3% |
| AA-Omniscience | -10.6 | 0.8 |
| Terminal-Bench Hard | – | 46.2% |
| GPQA Diamond (AA) | 92.4% | 92.8% |
| Humanity's Last Exam (AA) | 38.5% | 41.0% |
| SciCode (AA) | 51.6% | 51.0% |
| τ²-Bench Telecom (AA) | – | 96.2% |
| LiveCodeBench | – | 87.5% |
| MMLU-Pro | – | 87.3% |
| LegalBench | – | 80.3% |
| CorpFin | – | 61.4% |
| TaxEval | – | 72.1% |
| SWE-bench (Vals) | – | 77.4% |
| GPQA Diamond (Vals) | – | 89.4% |
| Vals Index | – | 42.9 |
| AIME 2026 | – | 96.7% |
| HMMT February 2026 | – | 93.9% |
| MathArena Apex | – | 28.1% |
| CritPt | 15.1% | 18.0% |
| GDPval (AA) | 53.7% | 49.7% |
| τ²-Bench Banking (AA) | 47.6% | 39.6% |
| ITBench SRE (AA) | – | 38.3% |
| Analyst Agent (AA) | – | 18.8% |
| APEX-Agents (AA) | – | 24.3% |
| CaseLaw v2 | – | 59.4% |
| Code Migration | – | 26.2% |
| Excel Modeling Benchmark | – | 51.6% |
| Finance Agent v2 | – | 44.1% |
| Harvey's Legal Agent Benchmark | – | 3.8% |
| Legal Research Bench | – | 23.1% |
| MedCode | – | 40.5% |
| MedScribe | – | 75.1% |
| ProgramBench | – | 0.0% |
| Public Benefits Bench | – | 62.9% |
| SkillsBench | – | 51.3% |
| Vibe Code Bench v1.1 | – | 49.9% |
| Chess Puzzles | – | 20.0% |
| LMCA | – | 41.2% |
| DTBench | – | 90.7% |
Data as of 2026-09-19. Best configuration of each model; every score links to its source on the model pages.
Agnes 3.0 Flash vs DeepSeek V4 Pro: questions
- Is Agnes 3.0 Flash better than DeepSeek V4 Pro?
- DeepSeek V4 Pro (max) leads on quality: 64.2 vs 62.3. The BenchLeader Index combines every independent quality benchmark; DeepSeek V4 Pro (max) is ahead overall as of 2026-09-19, but check the category scores for your use.
- Is Agnes 3.0 Flash better than DeepSeek V4 Pro for agentic tasks?
- Agnes 3.0 Flash scores higher in agentic tasks (77 vs 70 on the category index, where 50 is average).
- Which is cheaper, Agnes 3.0 Flash or DeepSeek V4 Pro?
- Agnes 3.0 Flash is cheaper: $0.075 against $0.544 per million tokens, blended at three input tokens per output token.
- Which has the larger context window?
- Both accept 1M tokens of context.