Skip to content

Language models

Intelligence, value, output speed, and explicit coverage gaps.

Snapshot: August 4, 2026

Math

Artificial Analysis Math Index · Higher is better

Eligible
0
Candidates
591
Coverage
0.0%

unavailable

No eligible math_index observations are available for this run.

Output speed

Median output tokens per second · Higher is better

Eligible
303
Candidates
591
Coverage
51.3%
Rank Model Creator Median output tokens per second Since prior snapshot
1 Celeris-1 Celeris 2,157.94 Not comparable
2 Mercury 2 Inception 788.13 Down 1
3 LFM2.5-VL-1.6B Liquid AI 397.67 Not comparable

Overall intelligence

Artificial Analysis Intelligence Index · Higher is better

Eligible
578
Candidates
591
Coverage
97.8%
Rank Model Creator Artificial Analysis Intelligence Index Since prior snapshot
1 Claude Opus 5 (Adaptive Reasoning, Max Effort) Anthropic 60.7 No change
2 Claude Opus 5 (Adaptive Reasoning, Xhigh Effort) Anthropic 60.1 No change
3 Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback) Anthropic 59.9 No change

Token-price value

Intelligence Index per local 3:1 blended token price · Higher is better

Eligible
373
Candidates
591
Coverage
63.1%
Rank Model Creator Intelligence Index per local 3:1 blended token price Since prior snapshot
1 Hy3-preview (Reasoning) Tencent 344.615 Not comparable
2 Qwen3.5 4B (Reasoning) Alibaba 335 Down 1
3 Gemma 4 E4B (Reasoning) Google 305 Down 1

Data source: Artificial Analysis .