Sports Film Review - Frames - svc-bench-3: leaderboard

Sports Film Review, svc-bench-3 (eyes), frames track (mariusCNN/sports-video-coach, 2026): a model reviews four synthetic sports videos (21 to 53 s) by eye and answers with numbers: the left player's foot touches while two players juggle (a count; double touches count twice, floor bounces not at all), made or missed for 12 shots at a far hoop, the release times of 12 passes between three players (four pass fakes are not passes), and a rower's stroke rate from 15 s, when the rate changes. The author built it for the frames track after strong models scored 1.0 on svc-bench-2 by eye: the events are small, short or hidden, so they have to be found still by still. The tool draws each video from numbers, so "the truth is exact. No human labels, no judge model." Unlike multiple-choice video QA, the answers are numbers: counts, rates, event timestamps and made/missed lists, each task scored 0 to 1 against that truth and then measured above a blind-guess floor (a deterministic guesser that sees no video and copies the example answers in the task text): per task above = clip((score - floor) / (1 - floor), 0, 1), and the suite score is the mean over its tasks. Frames track: no video and no code, only stills (one every 0.08 s) and contact sheets of 25 with the time printed under each still; Claude Code runs with --restricted --safe-mode --tools Read, Codex runs read-only with its shell and code-execution features disabled and sees only the contact sheets attached to the prompt (beyond that, its tool restriction is by prompt only). The suite is fixed: every draw is byte-identical, and its truth ships in the public package. Each row is the source's mean over the runs of one agent, model and settings configuration (1 to 2 runs per row on 2026-10-30); "A run killed at its time limit scores 0". A label suffix (Low, High, Max, xHigh) is the effort the row's settings name; rows without one state the default effort or none. Rows from a local Ollama quantisation are not listed. Higher is better. Source: https://mariuscnn.github.io/sports-video-coach/benchmark/

Metric: Mean score above the blind-guess floor (0-1). Source: mariuscnn.github.io. Saturation forecast: Around February 2027. 5 models tracked.

Top models

No result here: #7 GPT-6.1 Sol, #9 Gemini 4 Argon.

Interactive version: theaggregate.ai/benchmark?slug=sports-film-review-frames-svc-bench-3 · How It Works · Data refreshed daily, snapshot 2026-11-05.