BuilderBuilder
Research index

Choose a model. Inspect every run.

Start with the model, then open every benchmark and reasoning level tested with it. Public records keep the headline result, cost, time, record state, and evidence gaps visible. Paid research access adds the complete available ledger and disclosed configuration. Builder adds exact prompts, released projects, the RemakeBench Harness and production skills for the tests in its library.

Open the Launch 005 comparisonInspect Shrine Exploration
Published model index

Order by average cost or average time. Run count stays visible for context.

Download for Google SheetsCSV
21 models · 274 runs

2 models shown, ordered by average cost. 2 runs match the search.

01GLM 5.3 FlashOpenCode Go · Provider not separately recorded · Unavailable · ZCode · opencode-goMax28runs$1.5124/28 USD measured1h 1m14/28 measured02Gemini 3.8 FlashGoogle · OpenRouter · UnavailableHighHighest14runs$2.8014/14 USD measured54m 25s14/14 measured
Every public run

Every run, cost × time.

Compare individual model runs without flattening them into an average. The lower-left region is lower-cost and faster.

Run matrix2 measured runs on one field

Each dot is one public run. Cost runs left to right; wall-clock time runs bottom to top. Logarithmic spacing keeps the full range legible.

Wall-clock time
GLM 5.3 FlashDex Cube — 3 MoveMax · $1.44 · 1h 31mGemini 3.8 FlashDex Cube — 3 MoveHigh · $5.65 · 44m 30s
Measured workflow cost
GLM 5.3 Flash1Gemini 3.8 Flash1
RemakeBenchResearch console