ModelBench
Model catalog

Models

Every model in the catalog with source-linked pricing, context limits, provider availability, and published benchmark results.

Compare Export CSV
4 models
perplexity-agent Open weights
Ranked by Intelligence Index
Moonshot AI: Kimi K3 T
Reasoning Tools JSON Open weights 43.8

Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work

moonshotai/kimi-k3 2026-07-16 1.04858M context $3/M input $15/M output
63 providers
DeepSeek: DeepSeek V4 Flash 0731 T
Reasoning Tools JSON Open weights 34.5

Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding

deepseek/deepseek-v4-flash-0731 2026-07-31 1M context $0.035/M input $0.07/M output
43 providers
Moonshot AI: Kimi K2.7 Code T
Reasoning Tools JSON Open weights 26.3

Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking

moonshotai/kimi-k2.7-code 2026-06-12 262.144K context $0.95/M input $4/M output
61 providers
NVIDIA: Nemotron 3 Super 120B A12B T
Reasoning Open weights 13.6

Nemotron middle tier for collaborative agents and high-volume reasoning workloads

nvidia/nemotron-3-super-120b-a12b 2026-03-11 262.144K context $0.2/M input $0.8/M output
15 providers