- Intelligence
- 41.8
- Rank 54 of 744 measured models
- Coding
- 74.3
- Rank 32 of 298 measured models
- Output speed
- 58.3 t/s
- Rank 284 of 403 measured models
- Price/1M
- $10
- Rank 617 of 659 measured models
- Context window
- 1M
- Rank 84 of 1199 measured models
- Cost per task
- $4.08
- Rank 183 of 193 measured models
Claude Opus 4.8 (Max) scores 41.8 on the Artificial Analysis Intelligence Index, ranking 54th of 744 measured models. The closest models on this index are GPT-5.6 Terra (42.1), Claude Opus 4.8 (batch) (41.8), and GLM-5.3-Flash (41.8). At $10 per million tokens (3:1 input/output blended price), it is more expensive than GPT-5.6 Terra ($4.50) and GLM-5.3-Flash ($0.237). With an output speed of 58.3 t/s, it is slower than GPT-5.6 Terra (107 t/s) and GLM-5.3-Flash (62.3 t/s).
Additional benchmarks21
Design Arena · 3d51.7%
Design Arena · Agenticgamedev55.9%
Design Arena · Agentichtmlslides55.6%
Design Arena · Agenticslides Html56.0%
Design Arena · Agenticslides Python Pptx68.9%
Design Arena · Agenticslides64.8%
Design Arena · Androidnative56.4%
Design Arena · Asciiart62.3%
Design Arena · Codecategories52.5%
Design Arena · Dataviz52.8%
Design Arena · Fullstack55.3%
Design Arena · Gamedev52.8%
Design Arena · Godotgamedev55.8%
Design Arena · Htmlslides58.0%
Design Arena · Mobileapps55.5%
Design Arena · Pptxslides67.9%
Design Arena · Python Pptxslides65.9%
Design Arena · Svg51.4%
Design Arena · Uicomponent53.1%
Design Arena · Webapps51.4%
Design Arena · Website53.0%
Models at a similar level
The closest models on the Intelligence Index, one configuration per family.
- GPT-5.6 Terra
OpenAI · $4.50 · 107 t/s
42.1+0.3$4.50107 t/sCompare - Claude Opus 4.8 (batch)
Anthropic · — · —
41.8——Compare - GLM-5.3-Flash
Z.AI · $0.237 · 62.3 t/s
41.8$0.23762.3 t/sCompare - Ling 3.1 Flash
InclusionAI · $0.45 · 211 t/s
41.1−0.7$0.45211 t/sCompare
