Quality-first multi-agent model for hard research, analysis, and competitions
14 providers
Model catalog
Models
Every model in the catalog with source-linked pricing, context limits, provider availability, and published benchmark results.
Muse Spark Open is an 816B total / 42B active open-weight multimodal reasoning model from Meta for coding and long-horizon agentic work, with 1M-token context.
14 providers
Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks
34 providers
Sparse mixture-of-experts reasoning model with 23B active parameters for coding and agentic workflows
9 providers
Google's proven reasoning model for coding, math, and multimodal analysis
31 providers
Coding-optimized GPT model for repository edits, reviews, and agentic software work
13 providers
StepFun flash lane for quick multimodal reasoning and coding assistance
15 providers
Newer StepFun flash model for faster agents, coding, and multimodal prompts
21 providers
Fast Gemini workhorse for multimodal apps where latency and price matter
32 providers
Late GLM-4 workhorse for coding agents, reasoning, and structured tasks
21 providers
Flagship Qwen3 model for coding agents, complex reasoning, and tool use
23 providers
Fast Mistral production model for chat, extraction, and cost-sensitive agents
17 providers
Mistral's largest general model for enterprise agents, coding, and multilingual reasoning
16 providers
Mistral's coding-agent model for repository work, terminal tasks, and software fixes
13 providers
Fast NVIDIA Nemotron MoE for reliable agentic tasks across enterprise workloads
13 providers
Smaller Qwen coder for efficient local agents and repo-level fixes
13 providers
Deeper Sonar search model with broader retrieval and stronger synthesis
10 providers
Lean Gemini 2.5 lane for cheap multimodal traffic and quick agents
19 providers
| Model | Creator | Score | Inputs | Context | Input | Output | Released | Compare |
|---|---|---|---|---|---|---|---|---|
| Fugu Ultrasakana/fugu-ultra | Sakana |
58.7 | 1M | $5 | $30 | 2026-06-15 | ||
| Muse Spark Openmeta/muse-spark-open | Meta |
58.5 | 1.04858M | $1.25 | $4.25 | 2026-10-15 | ||
| Qwen3.7 Maxalibaba/qwen3.7-max | Alibaba Qwen |
53.5 | 1M | $2.5 | $7.5 | 2026-05-21 | ||
| Beam 1.0 501B A23Breflection/beam-1.0-501b-a23b | 49.2 | 1.04858M | $0.24 | $0.98 | 2026-10-05 | |||
| Gemini 2.5 Progoogle/gemini-2.5-pro | Google |
42.8 | 1.04858M | $1.25 | $10 | 2025-06-17 | ||
| GPT-5-Codexopenai/gpt-5-codex | OpenAI |
40.9 | 400K | $1.1 | $9 | 2025-09-15 | ||
| Step 3.5 Flashstepfun/step-3.5-flash | StepFun |
40.4 | 256K | $0.105 | $0.314 | 2026-01-29 | ||
| Step 3.7 Flashstepfun/step-3.7-flash | StepFun |
40.0 | 256K | $0.202 | $1.211 | 2026-05-29 | ||
| Gemini 2.5 Flashgoogle/gemini-2.5-flash | Google |
39.4 | 1.04858M | $0.3 | $2.5 | 2025-06-17 | ||
| GLM-4.6zhipuai/glm-4.6 | Zhipu AI |
38.4 | 204.8K | $0.6 | $2.2 | 2025-09-30 | ||
| Qwen3 Maxalibaba/qwen3-max | Alibaba Qwen |
38.3 | 262.144K | $1.2 | $6 | 2025-09-23 | ||
| Mistral Small 4mistral/mistral-small-2603 | Mistral AI |
38.0 | 256K | $0.15 | $0.6 | 2026-03-16 | ||
| Mistral Large 3mistral/mistral-large-2512 | Mistral AI |
36.2 | 262.144K | $0.5 | $1.5 | 2025-12-02 | ||
| Devstral 2mistral/devstral-2512 | Mistral AI |
33.1 | 262.144K | $0.4 | $2 | 2025-12-09 | ||
| Nemotron 3.5 Lightning 30B A3Bnvidia/nemotron-3.5-lightning | NVIDIA |
32.6 | 262.144K | $0.025 | $0.12 | 2026-08-11 | ||
| Qwen3-Coder 30B-A3B Instructalibaba/qwen3-coder-30b-a3b-instruct | Alibaba Qwen |
27.8 | 262.144K | $0.45 | $2.25 | 2025-07-31 | ||
| Sonar Properplexity/sonar-pro | Perplexity |
22.6 | 200K | $3 | $15 | 2024-01-01 | ||
| Gemini 2.5 Flash-Litegoogle/gemini-2.5-flash-lite | Google |
19.3 | 1.04858M | $0.1 | $0.4 | 2025-06-17 |