DeepSeekopen-weight
Released: 2024-12-26DeepSeek-V3
Ultra-cost-efficient open-weight MoE architecture offering near-frontier intelligence at a fraction of API costs.
Intelligence Index
82.4/ 100
Calibrated multi-domain compositeThroughput Speed
62tok/sec
Output streaming throughputTime To First Token
410ms
Initial chunk server latencyLiveBench Contam-Free
67.8%
September 2026 suite scoreLiveBench Multi-Domain Evaluation Breakdown
Monthly refreshed contamination-free test setsLogical Reasoning81.9%
Coding & Repo Repair69.2%
Mathematics (AIME)78.9%
Data Analysis & Tables74.2%
Language & Comprehension80.5%
Instruction Following87.5%
Sourced Benchmark Evaluations (5)
Verified performance across authoritative benchmarks with provenance tracking.| Benchmark | Status | Score | Trust | Date | Source Type | Provenance |
|---|---|---|---|---|---|---|
| StructFlowBench | Nearing Saturation | 96% | 75 | 2025-02-20 | independent | Source ↗ |
| ARC-AGI-2 | Nearing Saturation | 63.9% | 75 | 2025-01-23 | independent | Source ↗ |
| SWE-bench Verified | Saturated | 52.6% | 25 | 2025-01-04 | independent | Source ↗ |
| IFEval | Deprecated | 87.5% | 25 | 2024-12-30 | independent | Source ↗ |
| BIG-Bench Hard | Saturated | 87.5% | 25 | 2024-12-26 | vendor-reported | Source ↗ |
Local Hardware Execution (Ollama)Hardware Compatible
# 1. Pull and execute model locally with Ollama
ollama run deepseek-v3
# 2. Or invoke via local OpenAI-compatible endpoint
curl http://localhost:11434/v1/chat/completions \
-H "Content-Type: application/json" \
-d '{
"model": "deepseek-v3",
"messages": [{"role": "user", "content": "Analyze reasoning chains on AIME 2026"}]
}'Evaluation & Sourcing Notes
Scores listed for DeepSeek-V3 represent verified evaluations extracted from official research papers, independent evaluation suites (HELM, LMSYS, OpenCompass, LiveBench), and verified audit reports.
All benchmarks marked as saturated or deprecated reflect historical performance where the benchmark no longer provides active discriminative power.