Benchmark leaderboard
Terminal-Bench 2.1 Terminus 2 is a public benchmark board published by Terminal-Bench. ModelCap records each tracked model's published score and position on it without re-running the evaluation. This page lists every model ModelCap tracks with a published Terminal-Bench 2.1 Terminus 2 result, its best evaluated configuration, the source's own rank, and the model's ModelCap Index position, API price and context window.
Snapshot as of 5 June 2026
Claude Fable 5 from Anthropic leads the Terminal-Bench 2.1 Terminus 2 leaderboard among the 3 tracked models with 80.4 (High configuration), per the source snapshot published 5 June 2026.
Sorted by published score, one row per model. Source: Terminal-Bench.
Terminal-Bench 2.1 Terminus 2 ranks models by the published Terminal-Bench 2.1 Terminus 2 score. ModelCap ingests the board as published, matches each entry to a catalogue model with a reviewed identity, and shows the source's score, interval and rank unchanged. Where a model has an admitted result, it feeds the ModelCap Index as coding evidence alongside the other public boards; the methodology documents the weighting and the identity rules.
Terminal-Bench 2.1 Terminus 2 is a public benchmark board published by Terminal-Bench. ModelCap records each tracked model's published score and position on it without re-running the evaluation. It is published by Terminal-Bench.
Claude Fable 5 (Anthropic) holds the top Terminal-Bench 2.1 Terminus 2 score among the models ModelCap tracks, at 80.4 as of the source snapshot published 5 June 2026.
3 tracked models have a published Terminal-Bench 2.1 Terminus 2 result on ModelCap; the source board itself lists 5 entries. Each row shows the model's best evaluated configuration.
Among the ten highest-scoring priced models, Claude Opus 4.7 has the lowest listed output price at $25.00 per 1M tokens while scoring 66.1.
The board ranks models by the published Terminal-Bench 2.1 Terminus 2 score; higher scores are better. ModelCap shows the source's own score, interval and rank and never re-runs the evaluation.
Not on its own. The ModelCap Index combines several public capability sources with published uncertainty; Terminal-Bench 2.1 Terminus 2 contributes as coding evidence where a model has an admitted result. The methodology page documents the weighting.
The newest Terminal-Bench 2.1 Terminus 2 publication ModelCap holds is dated 5 June 2026. The page re-renders every minute from the sealed dataset, so it reflects the latest refresh of the source board.