Model pages
Models
Model pages from the current Artificial Analysis snapshots, with Intelligence Index scores, cost per task, and coding-agent results where they exist.
16 options
Showing 38 model cards.
Qwen3.8 Max
Claude Code
AAI43.3
Fable 5.1 Max
Claude Code
AAI62.2
Opus 5 Max
Claude Code
AAI59.7
Opus 5.5 Max
Claude Code
AAI66.0
Sonnet 5.5 Low
Claude Code
AAI42.1
Sonnet 5.5 Medium
Claude Code
AAI45.9
Sonnet 5.5 High
Claude Code
AAI55.0
Sonnet 5.5 X-high
Claude Code
AAI62.9
Sonnet 5.5 Max
Claude Code
AAI68.4
DeepSeek V4 Flash 0731 Max
Codex
AAI38.7
DeepSeek V4 Pro 0813 Max
Codex
AAI43.1
Gemini 3.8 Flash High
Antigravity SDK
AAI41.9
Gemini 4 Argon
Antigravity CLI
AAI63.8
Muse Spark 1.3 X-high
Muse Code
AAI48.3
Muse Spark 1.3 Max
Muse Code
AAI54.3
Kimi K3
Kimi Code CLI
AAI51.9
GPT-5.6 Luna Max
Codex
AAI43.2
GPT-5.6 Sol Max
Codex
AAI54.6
GPT-6 Astra Max
Codex
AAI61.6
GPT-6 Luna Max
Codex
AAI41.1
GPT-6 Sol Max
Codex
AAI56.7
GPT-6.1 Sol Low
Codex
AAI57.2
GPT-6.1 Sol Medium
Codex
AAI61.4
GPT-6.1 Sol High
Codex
AAI60.1
GPT-6.1 Sol X-high
Codex
AAI62.9
GPT-6.1 Sol Max
Codex
AAI60.1
Grok 4.6 X-high
Grok Build
AAI47.0
Grok 4.7 X-high
Grok Build
AAI56.3
Claude Fable 5.1 XHigh + SWE-2 Medium
Devin Fusion CLI
AAI61.7
GPT-6 Astra XHigh + SWE-2 Medium
Devin Fusion CLI
AAI58.9
GLM-5.3
Opencode
AAI53.6
Claude Haiku 5.5
Artificial Analysis Intelligence Index v4.3.2
Index43.4
Mistral Large 4 Preview
Artificial Analysis Intelligence Index v4.3.2
Index38.4
Ling 3.1 Flash
Artificial Analysis Intelligence Index v4.3.2
Index41.1
Solar Mini 4
Artificial Analysis Intelligence Index v4.3.2
Index24.1
MiMo-V2.6-Flash
Artificial Analysis Intelligence Index v4.3.2
Index37.9
MiMo-V2.6-Pro
Artificial Analysis Intelligence Index v4.3.2
Index46.3
Step 5 Preview
Artificial Analysis Intelligence Index v4.3.2
Index43.7
No cards match these filters. Try another provider or turn off Top.
First-party release radar
New releases found at first-party sources
24 labs · 30 first-party sourcesThese links come from each lab's own release pages, so a model can appear here before aggregators such as OpenRouter list it. The date shows when aicharts first found the page, which can differ from the official release date. Official dates and benchmark scores come from their own sources.
Release radar
New, awaiting complete benchmark coverage
26 incomplete · 5 with early DeepSWE · OpenRouter checked- Claude Haiku 5.5Anthropic · first observed
- GLM 5.3 FlashZ.ai · first observed Early DeepSWE 63.4% pass@1 · max · 4 runs · OpenRouter match
Models listed here do not yet have a complete result on the Artificial Analysis coding-agent chart. Where shown, an early DeepSWE v1.1 pass@1 comes straight from DataCurve's mini-swe-agent leaderboard, matched to the model through OpenRouter's catalog, or through Artificial Analysis when OpenRouter has no match. That result depends on DataCurve's harness, so it stays off the Artificial Analysis chart and model cards. Models with partial Artificial Analysis results can appear there, with missing metrics marked.