geekradar
Int
Explore GeekRadar

More to explore

Good gear All topics About us Say hello
GeekRadar / The comparison desk

COMPARE.

AI
Filters

Filter AI models

Brand
Benchmark coverage
Clear all filters

Best result per entry; configurations may differ.

Type
3 results Benchmark score
anthropic

Claude Opus 4.8

Models
Context window
1,000,000 tokens
Maximum output
128,000 tokens
Open weights
No
Maximum input
1,000,000 tokens*
SWE-bench Pro · version unreported · reported score · Claude Code · Refined task set with corrected problematic tasks#1* · 69.20*Platform unreported
ECI 159.6*General capability index
alibaba

Qwen 3.8 Max

Models
Context window
1,000,000 tokens*
Maximum output
131,072 tokens*
Open weights
No*
Reasoning
Yes*
SWE-bench Pro · version unreported · reported score · Claude Code · Refined task set with corrected problematic tasks#2* · 67.70*Platform unreported
ECI 158.0*General capability index
alibaba

Qwen3.7 Max

Models
Context window
1,000,000 tokens
Maximum output
131,072 tokens
Open weights
No
Reasoning
Yes
SWE-bench Pro · version unreported · reported score · Claude Code · Refined task set with corrected problematic tasks#3* · 60.60*Platform unreported
Radar · unrated0/4 core tests · not enough evidence

* Provisional data