Benchmarks · 2026-09-02

Do the best-scoring models win?

Independent LLM benchmark scores from OpenRouter's unified endpoint (Artificial Analysis composite indexes), cross-referenced with the token share those AI models receive on OpenRouter today.

Top 20 models — Intelligence

Higher is better. Bars coloured by lab.

Tidelines — LLM usage and market share
Data: OpenRouter · Artificial Analysis as of 2026-09-02 · Source: tidelines.ai/benchmarks

Efficiency frontier — Intelligence vs output price

Bubble = usage share. The line traces the Pareto frontier: models where nothing cheaper scores as high.

Tidelines — LLM usage and market share

How to read: X-axis is list output price (log); Y-axis is benchmark score; bubble area is current token share. The connecting line joins models that dominate on price-for-score.

Data: OpenRouter · list output price as of 2026-09-02 · Source: tidelines.ai/benchmarks

Benchmark score vs OpenRouter share — Intelligence

Top-right = high score AND heavily used · bottom-right = high score but under-adopted · top-left = popular despite lower score. Bubble size scales with usage share.

Tidelines — LLM usage and market share
Data: OpenRouter as of 2026-09-02 · Source: tidelines.ai/benchmarks

What a session actually costs in Hermes Agent

Median cost of one coding session by session length. 30-day window, log scale.

Agent
Tidelines — LLM usage and market share

GPT-5.6 Sol Pro costs 4246× more per session than gpt-oss-20b in this agent.

How to read: Each row is a model. Dots run from short sessions to long ones — the further right, the more a median session costs. The number on the right is the 10–49 turns median.

1 turn2–9 turns10–49 turns50+ turns
ModelMedian
Data: OpenRouter session-cost dataset as of 2026-08-30 · Source: tidelines.ai/benchmarks

Intelligence per dollar of real work

Benchmark score against the median 10–49 turns session cost in Hermes Agent.

Agent
Score
Tidelines — LLM usage and market share

Models on the dashed line are undominated: nothing is both cheaper and better-scoring. Bubble size is OpenRouter token share.

How to read: Cost runs left to right on a log scale, benchmark score bottom to top. Up and to the left is better value. Click a bubble for the model page.

Data: OpenRouter session-cost + Artificial Analysis as of 2026-08-30 · Source: tidelines.ai/benchmarks