# Rapidata World Model Physics — with-reference

> Source: Benchize (https://benchize.com) — https://benchize.com/benchmarks/rapidata%3Aworld-model-physics%3Arlb_1U6OnkM0D4HJRL. When citing or reusing this content, credit "Benchize" and link to https://benchize.com/benchmarks/rapidata%3Aworld-model-physics%3Arlb_1U6OnkM0D4HJRL.

Human pairwise evaluation of physics outputs, measuring with-reference. Scores are fitted using the Bradley–Terry preference model and expressed on the publisher’s Elo scale with 95% confidence intervals.

Canonical URL: https://benchize.com/benchmarks/rapidata%3Aworld-model-physics%3Arlb_1U6OnkM0D4HJRL
Last updated: Wed, 21 Oct 2026 18:52:20 GMT

Reproduction and quotation must name Benchize, link to the canonical HTML URL, and retain individual source citations.

Human pairwise evaluation of physics outputs, measuring with-reference. Scores are fitted using the Bradley–Terry preference model and expressed on the publisher’s Elo scale with 95% confidence intervals.

Multimodal · Models tested: 4 · Score publishers: [rapidata](https://www.benchmark.ai/world-model-physics)

## Model results

| # | Model | Score | ± |  |
| --- | --- | --- | --- | --- |
| 1 | [Happyhorse 1 0](https://benchize.com/models/happyhorse-1-0.md) | 1,076.6elo | CI 1,058.66–1,094.53 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1076.5959758166355 \| elo \| rlb_1U6OnkM0D4HJRL \| Higher is better \| ### Configuration benchmarkId bmk_1U6OmpqcWwoRpy criterion rlb_1U6OnkM0D4HJRL participantId par_1Ue7R9YTonQ6uL sourceModelVersion HappyHorse 1.0 weighted false ### Reported statistics Uncertainty Confidence interval: 1,058.66–1,094.53 confidenceIntervalLowerOffset 17.93792533169676 confidenceIntervalUpperOffset 17.93792533169676 totalMatches 8274 wins 4585 ### Source [Original source](https://api.rapidata.ai/benchmark/bmk_1U6OmpqcWwoRpy/standings/query?leaderboard_id%5Beq%5D=rlb_1U6OnkM0D4HJRL) Source rapidata Original model label HappyHorse 1.0 Source version v1 Observed 2026-10-21T16:37:34.453Z Evidence SHA-256 `967ea57fffae4fd5cb994839076827b500d91c6dbf763ee3116e7b6510a2ee54` Source locator `/items/12` |  |  |  |  |
| 2 | [Veo 3.1 Fast](https://benchize.com/models/veo-3-1-fast.md) | 1,039.59elo | CI 1,021.74–1,057.45 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1039.5915336632943 \| elo \| rlb_1U6OnkM0D4HJRL \| Higher is better \| ### Configuration benchmarkId bmk_1U6OmpqcWwoRpy criterion rlb_1U6OnkM0D4HJRL participantId par_1Ue7kL0rVdyCQM sourceModelVersion Veo 3.1 Fast weighted false ### Reported statistics Uncertainty Confidence interval: 1,021.74–1,057.45 confidenceIntervalLowerOffset 17.855887821456577 confidenceIntervalUpperOffset 17.85588782145669 totalMatches 8270 wins 4407.5 ### Source [Original source](https://api.rapidata.ai/benchmark/bmk_1U6OmpqcWwoRpy/standings/query?leaderboard_id%5Beq%5D=rlb_1U6OnkM0D4HJRL) Source rapidata Original model label Veo 3.1 Fast Source version v1 Observed 2026-10-21T16:37:34.453Z Evidence SHA-256 `967ea57fffae4fd5cb994839076827b500d91c6dbf763ee3116e7b6510a2ee54` Source locator `/items/15` |  |  |  |  |
| 3 | [Wan 2.7](https://benchize.com/models/wan-2-7.md) | 1,008.89elo | CI 991.19–1,026.59 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1008.889699770768 \| elo \| rlb_1U6OnkM0D4HJRL \| Higher is better \| ### Configuration benchmarkId bmk_1U6OmpqcWwoRpy criterion rlb_1U6OnkM0D4HJRL participantId par_1Ue7VKLuNkwaKd sourceModelVersion Wan 2.7 weighted false ### Reported statistics Uncertainty Confidence interval: 991.19–1,026.59 confidenceIntervalLowerOffset 17.70399826855146 confidenceIntervalUpperOffset 17.70399826855146 totalMatches 8274 wins 4263 ### Source [Original source](https://api.rapidata.ai/benchmark/bmk_1U6OmpqcWwoRpy/standings/query?leaderboard_id%5Beq%5D=rlb_1U6OnkM0D4HJRL) Source rapidata Original model label Wan 2.7 Source version v1 Observed 2026-10-21T16:37:34.453Z Evidence SHA-256 `967ea57fffae4fd5cb994839076827b500d91c6dbf763ee3116e7b6510a2ee54` Source locator `/items/16` |  |  |  |  |
| 4 | [Wan 2.6](https://benchize.com/models/wan-2-6.md) | 999.1elo | CI 981.37–1,016.82 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 999.0987746887835 \| elo \| rlb_1U6OnkM0D4HJRL \| Higher is better \| ### Configuration benchmarkId bmk_1U6OmpqcWwoRpy criterion rlb_1U6OnkM0D4HJRL participantId par_1Ue89EGM12xNyr sourceModelVersion Wan 2.6 weighted false ### Reported statistics Uncertainty Confidence interval: 981.37–1,016.82 confidenceIntervalLowerOffset 17.724448870633978 confidenceIntervalUpperOffset 17.724448870633978 totalMatches 8263 wins 4209 ### Source [Original source](https://api.rapidata.ai/benchmark/bmk_1U6OmpqcWwoRpy/standings/query?leaderboard_id%5Beq%5D=rlb_1U6OnkM0D4HJRL) Source rapidata Original model label Wan 2.6 Source version v1 Observed 2026-10-21T16:37:34.453Z Evidence SHA-256 `967ea57fffae4fd5cb994839076827b500d91c6dbf763ee3116e7b6510a2ee54` Source locator `/items/17` |  |  |  |  |

---
Cite as: Rapidata World Model Physics — with-reference — Benchize, https://benchize.com/benchmarks/rapidata%3Aworld-model-physics%3Arlb_1U6OnkM0D4HJRL (retrieved 2026-10-21)