Home › Results

Every model, every page it made

Search by name, or narrow by provider, model, effort, video and test. Open a run for its files, or compare two models. Every score in one table (CSV), with links back to each page.

Score sorting is available across all results. Mixed historical scores describe different work; use comparison filters for equivalent tests. Resource columns show full-run use.

22 of 22 runs

Model
Score / basis
Time
Output tokens
Cost
Recorded in
glm-5.3-flash:cloudeffort: highpartial quality coverageZ.ai · 4 Oct 2026
5.4 / 10Quality v1 · 7/8 pages
Time1h 44m
Output tokens≥699k
Cost—
—
Kolibri-1-MLX-4biteffort: defaultpartial quality coverageOther · 4 Oct 2026
1.8 / 10Quality v1 · 7/8 pages
Time59m 32s
Output tokens199k
CostNo API chargelocal
—
kimi-k3:cloudeffort: defaultMoonshotAI · 3 Oct 2026
4.5 / 10Quality v1 · 8/8 pages
Time1h 42m
Output tokens≥581k
Cost—
—
x-ai/grok-4.7effort: defaultpartial quality coverageSpaceXAI · 3 Oct 2026
3.4 / 10Quality v1 · 1/2 pages
Time1h 03m
Output tokens≥144k
Cost≥≈$5.24API price, est.
—
gpt-6-lunaeffort: highOpenAI · 2 Oct 2026
3.5 / 10Quality v1 · 1/1 pages
Time5m 12s
Output tokens17k
Cost≈$0.01API price, est.
—
qwen3.8:27b-mlxeffort: defaultQwen · 1 Oct 2026
2.1 / 10Quality v1 · 5/5 pages
Time1h 49m
Output tokens202k
CostNo API chargelocal
—
openai/gpt-6-lunaeffort: defaultOpenAI · 27 Sept 2026
3.6 / 10Quality v1 · 5/5 pages
Time11m 51s
Output tokens107k
Cost—
—