1. 7API
  2. Benchmarks

LLM benchmarks: intelligence and price

Independent benchmark results for the models available on 7API, from the Artificial Analysis Intelligence Index, shown next to each model's 7API price. 7API doesn't run these evaluations. Every score links to its public source.

Highlights

Artificial Analysis Intelligence Index

A composite of ten evaluations run independently by Artificial Analysis: AA-Briefcase, GDPval-AA, AutomationBench-AA, Terminal-Bench 4.0, SciCode, Humanity's Last Exam, GDP.pdf, CritPt, AA-Omniscience and AA-LCR. It covers agentic work, coding, science, reasoning and long-context retrieval. Higher is better. The top score at the time of retrieval was 58. Each model is shown at its best-scoring effort level. Source · v4.3.2, retrieved 2026-10-24.

Artificial Analysis Intelligence Index v4.3.2, best effort level per model. Scale 0–60.
ModelScoreEffort7API price / 1MContext
Claude Opus 5.558max$0.701M
Claude Sonnet 5.556max$0.501M
Kimi K3.1 Pro55default$0.301M
Gemini 4 Argon53high$0.30128K
GPT-6 Astra53max$0.651.05M
GPT-6.1 Sol52max$0.151.05M
Grok 4.746xhigh$0.10500K
DeepSeek V4.1 Flash 101745max$0.021M
GLM 5.345max$0.051M
Claude Haiku 5.543max$0.031M
GLM 5.3 Flash42default$0.0251M
GPT-5.6 Terra42max$0.451M
GPT-6 Luna38max$0.051.05M
DeepSeek V4 Pro36max$0.251M

Score by effort level

Reasoning effort changes the score a lot. The index lists the same model at several effort levels, and 7API accepts all of them (see Reasoning effort).

Modelmaxxhighhighmediumlow
Claude Opus 5.55856545142
Claude Sonnet 5.55652474136
GPT-6 Astra5352515046
GPT-6.1 Sol5251504842
Grok 4.7—4646—42
Claude Haiku 5.54341383429
GPT-5.6 Terra4238343027
GPT-6 Luna3835333022

Capability per dollar

Intelligence Index score plotted against the 7API standard rate (input and output cost the same per token).

30405060 $0.01$0.03$0.1$0.3$1 7API price per 1M tokens (log scale) → ← Intelligence Index Claude Opus 5.5: score 58, $0.70/MOpus 5.5Claude Sonnet 5.5: score 56, $0.50/MSonnet 5.5Kimi K3.1 Pro: score 55, $0.30/MKimi K3.1 ProGemini 4 Argon: score 53, $0.30/MGemini 4 ArgonGPT-6 Astra: score 53, $0.65/MGPT-6 AstraGPT-6.1 Sol: score 52, $0.15/MGPT-6.1 SolGrok 4.7: score 46, $0.10/MGrok 4.7DeepSeek V4.1 Flash 1017: score 45, $0.02/MV4.1 Flash 1017GLM 5.3: score 45, $0.05/MGLM 5.3Claude Haiku 5.5: score 43, $0.03/MHaiku 5.5GLM 5.3 Flash: score 42, $0.025/MGLM 5.3 FlashGPT-5.6 Terra: score 42, $0.45/MGPT-5.6 TerraGPT-6 Luna: score 38, $0.05/MGPT-6 LunaDeepSeek V4 Pro: score 36, $0.25/MV4 Pro
Up and to the left is better: more capability per dollar. Hover or tap a dot for exact values.

Method and caveats

Last updated 2026-10-24.