Loading benchmark catalogue
Compare performance benchmarks, coding intelligence, reasoning evaluations, context limits, and API economics between DeepSeek V4 Pro 0813 (DeepSeek) and Kimi K3.1 Pro (Moonshot AI).
| Metric / Capability | DeepSeek V4 Pro 0813 | Kimi K3.1 Pro |
|---|---|---|
| Developer / Organization | DeepSeek | Moonshot AI |
| Release Date | 2026-08-12 | 2026-10-23 |
| Deployment / Weights | Open Weights | Proprietary Cloud API |
| Context Window | 1.0M tokens (1,048,576 tokens) | 1.0M tokens (1,048,576 tokens) |
| Input Pricing (/1M Tokens) | Free (Open Weights) | $2 |
| Output Pricing (/1M Tokens) | Free (Open Weights) | $10 |
| Benchmark / Domain | DeepSeek V4 Pro 0813 | Kimi K3.1 Pro | Advantage |
|---|---|---|---|
Artificial Analysis Intelligence Index Composite index aggregating 10+ evaluations of general reasoning and knowledge. | 36.0% | 55.1% | Kimi K3.1 Pro (+53%) |
Artificial Analysis Coding Index Composite index of coding and software-engineering evaluations. | 68.8% | — | — |
Artificial Analysis Agentic Index Composite index of tool-use and long-horizon agentic tasks. | 41.3% | — | — |
SWE-bench Pro Harder, contamination-resistant successor to SWE-bench spanning multiple languages. | 55.4% | — | — |
Terminal-Bench 4.0 Sandboxed command-line tasks requiring shell and file-system operation. | — | 65.7% | — |
ARC-AGI-2 Novel visual grid puzzles requiring abstract rule induction. | 61.3% | — | — |
GPQA Diamond Graduate-level physics, chemistry, and biology questions written by domain experts. | 90.1% | 94.2% | Kimi K3.1 Pro (+5%) |
Humanity's Last Exam Expert-written questions across hundreds of disciplines designed to resist saturation. | 42.7% | 51.1% | Kimi K3.1 Pro (+20%) |
FrontierMath v2 (Tiers 1-3) Unpublished, research-level mathematics problems across Tiers 1-3. | 45.3% | — | — |
Design Arena ELO Human-preference ELO across UI, 3D, data-visualization, and game-dev generations. | — | 1448 | — |
Kimi K3.1 Pro outperforms DeepSeek V4 Pro 0813 across 3 evaluated benchmarks compared to 0 for DeepSeek V4 Pro 0813, excelling in Artificial Analysis Intelligence Index, GPQA Diamond, Humanity's Last Exam.
Both models feature equivalent context windows of 1.0M tokens (1,048,576 tokens).
DeepSeek V4 Pro 0813 is more cost-effective. Input tokens cost $Free (Open Weights)/M tokens vs $2/M tokens for Kimi K3.1 Pro.
DeepSeek V4 Pro 0813 is an open-weights model. Kimi K3.1 Pro is a proprietary cloud API.
Analyze 130+ models side-by-side using interactive radar charts, cost-efficiency quadrant plots, and live dataset filters on the full NeuBench index.
Open Interactive Comparator