Loading benchmark catalogue
Compare performance benchmarks, coding intelligence, reasoning evaluations, context limits, and API economics between Gemini 3.8 Flash (Google DeepMind) and Kimi K3.1 Pro (Moonshot AI).
| Metric / Capability | Gemini 3.8 Flash | Kimi K3.1 Pro |
|---|---|---|
| Developer / Organization | Google DeepMind | Moonshot AI |
| Release Date | 2026-09-02 | 2026-10-23 |
| Deployment / Weights | Proprietary Cloud API | Proprietary Cloud API |
| Context Window | 1.0M tokens (1,048,576 tokens) | 1.0M tokens (1,048,576 tokens) |
| Input Pricing (/1M Tokens) | $0.825 | $2 |
| Output Pricing (/1M Tokens) | $4.125 | $10 |
| Benchmark / Domain | Gemini 3.8 Flash | Kimi K3.1 Pro | Advantage |
|---|---|---|---|
Artificial Analysis Intelligence Index Composite index aggregating 10+ evaluations of general reasoning and knowledge. | 40.9% | 55.1% | Kimi K3.1 Pro (+35%) |
Artificial Analysis Coding Index Composite index of coding and software-engineering evaluations. | 76.3% | — | — |
Artificial Analysis Agentic Index Composite index of tool-use and long-horizon agentic tasks. | 40.2% | — | — |
Artificial Analysis Coding Agent Index v2.0 Composite index of coding-agent systems (model + harness) across FrontierCode v1.1, SWE-Atlas-QnA, and Terminal-Bench v4. | 33.3% | — | — |
Terminal-Bench 4.0 Sandboxed command-line tasks requiring shell and file-system operation. | 19.1% | 65.7% | Kimi K3.1 Pro (+244%) |
ARC-AGI-2 Novel visual grid puzzles requiring abstract rule induction. | 89.2% | — | — |
GPQA Diamond Graduate-level physics, chemistry, and biology questions written by domain experts. | — | 94.2% | — |
Humanity's Last Exam Expert-written questions across hundreds of disciplines designed to resist saturation. | — | 51.1% | — |
FrontierMath v2 (Tiers 1-3) Unpublished, research-level mathematics problems across Tiers 1-3. | 68.4% | — | — |
Design Arena ELO Human-preference ELO across UI, 3D, data-visualization, and game-dev generations. | 1313 | 1448 | Kimi K3.1 Pro (+10%) |
Kimi K3.1 Pro outperforms Gemini 3.8 Flash across 3 evaluated benchmarks compared to 0 for Gemini 3.8 Flash, excelling in Artificial Analysis Intelligence Index, Terminal-Bench 4.0, Design Arena ELO.
Both models feature equivalent context windows of 1.0M tokens (1,048,576 tokens).
Gemini 3.8 Flash is more cost-effective. Input tokens cost $0.825/M tokens vs $2/M tokens for Kimi K3.1 Pro.
Gemini 3.8 Flash is a proprietary cloud API. 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