# PRBench Legal > Source: Benchize (https://benchize.com) — https://benchize.com/benchmarks/scale%3Aprbench-legal. When citing or reusing this content, credit "Benchize" and link to https://benchize.com/benchmarks/scale%3Aprbench-legal. Realistic legal reasoning tasks graded against detailed expert-written criteria for professional work. Canonical URL: https://benchize.com/benchmarks/scale%3Aprbench-legal 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. Realistic legal reasoning tasks graded against detailed expert-written criteria for professional work. Professional work · Models tested: 26 · Score publishers: [scale](https://labs.scale.com/leaderboard/prbench-legal) ## Model results | # | Model | Score | ± | | | --- | --- | --- | --- | --- | | 1 | [Muse Spark 1.3](https://benchize.com/models/muse-spark-1-3.md) | 61.56source score | CI 59.84–63.28 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 61.56 \| source_score \| reported \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration Muse Spark 1.3 sourceModelVersion Not reported thinkingEnabled Not reported ### Reported statistics Uncertainty Confidence interval: 59.84–63.28 contaminationWarning Not reported rank 1 reportedConfidenceHalfWidth 1.72 ### Source [Original source](https://labs.scale.com/leaderboard/prbench-legal) Source scale Original model label Muse Spark 1.3 Observed 2026-10-21T16:35:35.197Z Evidence SHA-256 `9e2ca4e9350870cf508bf5fff603d0b795c81f7974a0ab980312bbbfa0785067` Source locator `/rows/0` | | | | | | 2 | [Muse Spark Open](https://benchize.com/models/muse-spark-open.md) | 59.76source score | CI 58.88–60.64 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 59.76 \| source_score \| reported \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration Muse Spark Open sourceModelVersion fireworks_ai/muse-spark-open thinkingEnabled Not reported ### Reported statistics Uncertainty Confidence interval: 58.88–60.64 contaminationWarning Not reported rank 2 reportedConfidenceHalfWidth 0.88 ### Source [Original source](https://labs.scale.com/leaderboard/prbench-legal) Source scale Original model label Muse Spark Open Observed 2026-10-21T16:35:35.197Z Evidence SHA-256 `9e2ca4e9350870cf508bf5fff603d0b795c81f7974a0ab980312bbbfa0785067` Source locator `/rows/1` | | | | | | 3 | [Muse Spark 1.1](https://benchize.com/models/muse-spark-1-1.md) | 57.05source score | CI 56.83–57.27 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 57.05 \| source_score \| reported \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration Muse Spark 1.1 sourceModelVersion Not reported thinkingEnabled Not reported ### Reported statistics Uncertainty Confidence interval: 56.83–57.27 contaminationWarning Not reported rank 4 reportedConfidenceHalfWidth 0.22 ### Source [Original source](https://labs.scale.com/leaderboard/prbench-legal) Source scale Original model label Muse Spark 1.1 Observed 2026-10-21T16:35:35.197Z Evidence SHA-256 `9e2ca4e9350870cf508bf5fff603d0b795c81f7974a0ab980312bbbfa0785067` Source locator `/rows/3` | | | | | | 4 | [Claude Fable 5](https://benchize.com/models/claude-fable-5.md) | 52.56source score | CI 52.02–53.1 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 52.56 \| source_score \| reported \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration claude-fable 5 sourceModelVersion Not reported thinkingEnabled Not reported ### Reported statistics Uncertainty Confidence interval: 52.02–53.1 contaminationWarning Not reported rank 5 reportedConfidenceHalfWidth 0.54 ### Source [Original source](https://labs.scale.com/leaderboard/prbench-legal) Source scale Original model label claude-fable 5 Observed 2026-10-21T16:35:35.197Z Evidence SHA-256 `9e2ca4e9350870cf508bf5fff603d0b795c81f7974a0ab980312bbbfa0785067` Source locator `/rows/4` | | | | | | 5 | [Claude Opus 4.6](https://benchize.com/models/claude-opus-4-6-off.md)Non-thinking | 52.27source score | CI 51.61–52.92 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 52.265 \| source_score \| reported \| Higher is better \| ### Configuration Reasoning effort non-thinking Model configuration claude-opus-4-6 (Non-Thinking) sourceModelVersion Not reported thinkingEnabled false ### Reported statistics Uncertainty Confidence interval: 51.61–52.92 contaminationWarning Not reported rank 7 reportedConfidenceHalfWidth 0.6555 ### Source [Original source](https://labs.scale.com/leaderboard/prbench-legal) Source scale Original model label claude-opus-4-6 (Non-Thinking) Observed 2026-10-21T16:35:35.197Z Evidence SHA-256 `9e2ca4e9350870cf508bf5fff603d0b795c81f7974a0ab980312bbbfa0785067` Source locator `/rows/6` | | | | | | 6 | [GPT-5.6 Sol](https://benchize.com/models/gpt-5-6-sol-max.md)Max | 50.5source score | CI 49.96–51.04 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 50.5 \| source_score \| reported \| Higher is better \| ### Configuration Reasoning effort max Model configuration gpt-5.6-sol (max) sourceModelVersion Not reported thinkingEnabled true ### Reported statistics Uncertainty Confidence interval: 49.96–51.04 contaminationWarning Not reported rank 9 reportedConfidenceHalfWidth 0.54 ### Source [Original source](https://labs.scale.com/leaderboard/prbench-legal) Source scale Original model label gpt-5.6-sol (max) Observed 2026-10-21T16:35:35.197Z Evidence SHA-256 `9e2ca4e9350870cf508bf5fff603d0b795c81f7974a0ab980312bbbfa0785067` Source locator `/rows/8` | | | | | | 7 | [GPT-5 Pro](https://benchize.com/models/gpt-5-pro.md) | 49.89source score | CI 49.53–50.25 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 49.89389865 \| source_score \| reported \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration gpt-5-pro sourceModelVersion Not reported thinkingEnabled Not reported ### Reported statistics Uncertainty Confidence interval: 49.53–50.25 contaminationWarning Not reported rank 10 reportedConfidenceHalfWidth 0.3589786494 ### Source [Original source](https://labs.scale.com/leaderboard/prbench-legal) Source scale Original model label gpt-5-pro Observed 2026-10-21T16:35:35.197Z Evidence SHA-256 `9e2ca4e9350870cf508bf5fff603d0b795c81f7974a0ab980312bbbfa0785067` Source locator `/rows/9` | | | | | | 8 | [O3 Pro](https://benchize.com/models/o3-pro.md) | 49.67source score | CI 49.17–50.18 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 49.67254409 \| source_score \| reported \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration o3-pro sourceModelVersion Not reported thinkingEnabled Not reported ### Reported statistics Uncertainty Confidence interval: 49.17–50.18 contaminationWarning Not reported rank 11 reportedConfidenceHalfWidth 0.5039224562 ### Source [Original source](https://labs.scale.com/leaderboard/prbench-legal) Source scale Original model label o3-pro Observed 2026-10-21T16:35:35.197Z Evidence SHA-256 `9e2ca4e9350870cf508bf5fff603d0b795c81f7974a0ab980312bbbfa0785067` Source locator `/rows/10` | | | | | | 9 | [Gemini 4 Argon](https://benchize.com/models/gemini-4-argon.md) | 49.41source score | CI 49.04–49.78 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 49.41 \| source_score \| reported \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration Gemini 4 Argon sourceModelVersion gemini/gemini-4-argon thinkingEnabled Not reported ### Reported statistics Uncertainty Confidence interval: 49.04–49.78 contaminationWarning Not reported rank 12 reportedConfidenceHalfWidth 0.37 ### Source [Original source](https://labs.scale.com/leaderboard/prbench-legal) Source scale Original model label Gemini 4 Argon Observed 2026-10-21T16:35:35.197Z Evidence SHA-256 `9e2ca4e9350870cf508bf5fff603d0b795c81f7974a0ab980312bbbfa0785067` Source locator `/rows/11` | | | | | | 10 | [GPT-5](https://benchize.com/models/gpt-5.md) | 48.96source score | CI 48.93–48.99 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 48.96127165 \| source_score \| reported \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration gpt-5 sourceModelVersion Not reported thinkingEnabled Not reported ### Reported statistics Uncertainty Confidence interval: 48.93–48.99 contaminationWarning Not reported rank 14 reportedConfidenceHalfWidth 0.02813447719 ### Source [Original source](https://labs.scale.com/leaderboard/prbench-legal) Source scale Original model label gpt-5 Observed 2026-10-21T16:35:35.197Z Evidence SHA-256 `9e2ca4e9350870cf508bf5fff603d0b795c81f7974a0ab980312bbbfa0785067` Source locator `/rows/13` | | | | | | 11 | [Gemini 3.8 Flash](https://benchize.com/models/gemini-3-8-flash.md) | 48.9source score | CI 47.25–50.55 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 48.9 \| source_score \| reported \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration Gemini 3.8 Flash sourceModelVersion Not reported thinkingEnabled Not reported ### Reported statistics Uncertainty Confidence interval: 47.25–50.55 contaminationWarning Not reported rank 15 reportedConfidenceHalfWidth 1.65 ### Source [Original source](https://labs.scale.com/leaderboard/prbench-legal) Source scale Original model label Gemini 3.8 Flash Observed 2026-10-21T16:35:35.197Z Evidence SHA-256 `9e2ca4e9350870cf508bf5fff603d0b795c81f7974a0ab980312bbbfa0785067` Source locator `/rows/14` | | | | | | 12 | [O3](https://benchize.com/models/o3.md) | 48.57source score | CI 48.03–49.11 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 48.57241633 \| source_score \| reported \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration o3 sourceModelVersion Not reported thinkingEnabled Not reported ### Reported statistics Uncertainty Confidence interval: 48.03–49.11 contaminationWarning Not reported rank 16 reportedConfidenceHalfWidth 0.5383550717 ### Source [Original source](https://labs.scale.com/leaderboard/prbench-legal) Source scale Original model label o3 Observed 2026-10-21T16:35:35.197Z Evidence SHA-256 `9e2ca4e9350870cf508bf5fff603d0b795c81f7974a0ab980312bbbfa0785067` Source locator `/rows/15` | | | | | | 13 | [GPT-6 Astra](https://benchize.com/models/gpt-6-astra.md) | 48.36source score | CI 46.72–50 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 48.36 \| source_score \| reported \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration GPT 6 Astra sourceModelVersion Not reported thinkingEnabled Not reported ### Reported statistics Uncertainty Confidence interval: 46.72–50 contaminationWarning Not reported rank 17 reportedConfidenceHalfWidth 1.64 ### Source [Original source](https://labs.scale.com/leaderboard/prbench-legal) Source scale Original model label GPT 6 Astra Observed 2026-10-21T16:35:35.197Z Evidence SHA-256 `9e2ca4e9350870cf508bf5fff603d0b795c81f7974a0ab980312bbbfa0785067` Source locator `/rows/16` | | | | | | 14 | [GPT-6.1 Sol](https://benchize.com/models/gpt-6-1-sol.md) | 47.87source score | CI 46.18–49.56 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 47.87 \| source_score \| reported \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration GPT 6.1 Sol sourceModelVersion gpt-6.1-sol thinkingEnabled Not reported ### Reported statistics Uncertainty Confidence interval: 46.18–49.56 contaminationWarning Not reported rank 18 reportedConfidenceHalfWidth 1.69 ### Source [Original source](https://labs.scale.com/leaderboard/prbench-legal) Source scale Original model label GPT 6.1 Sol Observed 2026-10-21T16:35:35.197Z Evidence SHA-256 `9e2ca4e9350870cf508bf5fff603d0b795c81f7974a0ab980312bbbfa0785067` Source locator `/rows/17` | | | | | | 15 | [Claude Opus 5.5](https://benchize.com/models/claude-opus-5-5.md) | 47.58source score | CI 45.38–49.78 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 47.58 \| source_score \| reported \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration claude-opus-5-5 sourceModelVersion Not reported thinkingEnabled Not reported ### Reported statistics Uncertainty Confidence interval: 45.38–49.78 contaminationWarning Not reported rank 20 reportedConfidenceHalfWidth 2.2 ### Source [Original source](https://labs.scale.com/leaderboard/prbench-legal) Source scale Original model label claude-opus-5-5 Observed 2026-10-21T16:35:35.197Z Evidence SHA-256 `9e2ca4e9350870cf508bf5fff603d0b795c81f7974a0ab980312bbbfa0785067` Source locator `/rows/19` | | | | | | 16 | [GPT-5.4](https://benchize.com/models/gpt-5-4-high.md)High | 44.35source score | CI 44.07–44.63 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 44.35 \| source_score \| reported \| Higher is better \| ### Configuration Reasoning effort high Model configuration gpt-5.4 (High) sourceModelVersion Not reported thinkingEnabled true ### Reported statistics Uncertainty Confidence interval: 44.07–44.63 contaminationWarning Not reported rank 22 reportedConfidenceHalfWidth 0.278 ### Source [Original source](https://labs.scale.com/leaderboard/prbench-legal) Source scale Original model label gpt-5.4 (High) Observed 2026-10-21T16:35:35.197Z Evidence SHA-256 `9e2ca4e9350870cf508bf5fff603d0b795c81f7974a0ab980312bbbfa0785067` Source locator `/rows/21` | | | | | | 17 | [Gemini 3.1 Pro](https://benchize.com/models/gemini-3-1-pro.md) | 44.02source score | CI 42.9–45.14 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 44.0231 \| source_score \| reported \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration gemini-3.1-pro sourceModelVersion Not reported thinkingEnabled Not reported ### Reported statistics Uncertainty Confidence interval: 42.9–45.14 contaminationWarning Not reported rank 24 reportedConfidenceHalfWidth 1.1208 ### Source [Original source](https://labs.scale.com/leaderboard/prbench-legal) Source scale Original model label gemini-3.1-pro Observed 2026-10-21T16:35:35.197Z Evidence SHA-256 `9e2ca4e9350870cf508bf5fff603d0b795c81f7974a0ab980312bbbfa0785067` Source locator `/rows/23` | | | | | | 18 | [GPT-6 Luna](https://benchize.com/models/gpt-6-luna.md) | 42.85source score | CI 41.16–44.54 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 42.85 \| source_score \| reported \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration gpt-6-luna sourceModelVersion Not reported thinkingEnabled Not reported ### Reported statistics Uncertainty Confidence interval: 41.16–44.54 contaminationWarning Not reported rank 26 reportedConfidenceHalfWidth 1.69 ### Source [Original source](https://labs.scale.com/leaderboard/prbench-legal) Source scale Original model label gpt-6-luna Observed 2026-10-21T16:35:35.197Z Evidence SHA-256 `9e2ca4e9350870cf508bf5fff603d0b795c81f7974a0ab980312bbbfa0785067` Source locator `/rows/25` | | | | | | 19 | [Gemini 2.5 Pro](https://benchize.com/models/gemini-2-5-pro.md) | 41.43source score | CI 41.23–41.63 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 41.42704353 \| source_score \| reported \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration gemini-2.5-pro sourceModelVersion Not reported thinkingEnabled Not reported ### Reported statistics Uncertainty Confidence interval: 41.23–41.63 contaminationWarning Not reported rank 27 reportedConfidenceHalfWidth 0.201882702 ### Source [Original source](https://labs.scale.com/leaderboard/prbench-legal) Source scale Original model label gemini-2.5-pro Observed 2026-10-21T16:35:35.197Z Evidence SHA-256 `9e2ca4e9350870cf508bf5fff603d0b795c81f7974a0ab980312bbbfa0785067` Source locator `/rows/26` | | | | | | 20 | [Gemini 2.5 Flash](https://benchize.com/models/gemini-2-5-flash.md) | 41.02source score | CI 40.4–41.63 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 41.01527724 \| source_score \| reported \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration gemini-2.5-flash sourceModelVersion Not reported thinkingEnabled Not reported ### Reported statistics Uncertainty Confidence interval: 40.4–41.63 contaminationWarning Not reported rank 28 reportedConfidenceHalfWidth 0.6112592141 ### Source [Original source](https://labs.scale.com/leaderboard/prbench-legal) Source scale Original model label gemini-2.5-flash Observed 2026-10-21T16:35:35.197Z Evidence SHA-256 `9e2ca4e9350870cf508bf5fff603d0b795c81f7974a0ab980312bbbfa0785067` Source locator `/rows/27` | | | | | | 21 | [gpt-oss-120b](https://benchize.com/models/gpt-oss-120b.md) | 40.21source score | CI 38.14–42.27 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 40.20563979 \| source_score \| reported \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration gpt-oss-120b sourceModelVersion Not reported thinkingEnabled Not reported ### Reported statistics Uncertainty Confidence interval: 38.14–42.27 contaminationWarning Not reported rank 32 reportedConfidenceHalfWidth 2.06866142 ### Source [Original source](https://labs.scale.com/leaderboard/prbench-legal) Source scale Original model label gpt-oss-120b Observed 2026-10-21T16:35:35.197Z Evidence SHA-256 `9e2ca4e9350870cf508bf5fff603d0b795c81f7974a0ab980312bbbfa0785067` Source locator `/rows/31` | | | | | | 22 | [GPT-6 Sol](https://benchize.com/models/gpt-6-sol.md) | 38.6source score | CI 37.02–40.18 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 38.6 \| source_score \| reported \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration gpt-6-sol sourceModelVersion Not reported thinkingEnabled Not reported ### Reported statistics Uncertainty Confidence interval: 37.02–40.18 contaminationWarning Not reported rank 34 reportedConfidenceHalfWidth 1.58 ### Source [Original source](https://labs.scale.com/leaderboard/prbench-legal) Source scale Original model label gpt-6-sol Observed 2026-10-21T16:35:35.197Z Evidence SHA-256 `9e2ca4e9350870cf508bf5fff603d0b795c81f7974a0ab980312bbbfa0785067` Source locator `/rows/33` | | | | | | 23 | [O4 Mini](https://benchize.com/models/o4-mini.md) | 38.11source score | CI 37.43–38.8 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 38.11371849 \| source_score \| reported \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration o4-mini sourceModelVersion Not reported thinkingEnabled Not reported ### Reported statistics Uncertainty Confidence interval: 37.43–38.8 contaminationWarning Not reported rank 36 reportedConfidenceHalfWidth 0.6861079648 ### Source [Original source](https://labs.scale.com/leaderboard/prbench-legal) Source scale Original model label o4-mini Observed 2026-10-21T16:35:35.197Z Evidence SHA-256 `9e2ca4e9350870cf508bf5fff603d0b795c81f7974a0ab980312bbbfa0785067` Source locator `/rows/35` | | | | | | 24 | [R1 0528](https://benchize.com/models/deepseek-r1-0528.md) | 36.61source score | CI 35.93–37.29 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 36.6094653 \| source_score \| reported \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration deepseek-r1-0528 sourceModelVersion Not reported thinkingEnabled Not reported ### Reported statistics Uncertainty Confidence interval: 35.93–37.29 contaminationWarning Not reported rank 38 reportedConfidenceHalfWidth 0.682238965 ### Source [Original source](https://labs.scale.com/leaderboard/prbench-legal) Source scale Original model label deepseek-r1-0528 Observed 2026-10-21T16:35:35.197Z Evidence SHA-256 `9e2ca4e9350870cf508bf5fff603d0b795c81f7974a0ab980312bbbfa0785067` Source locator `/rows/37` | | | | | | 25 | [GPT-4.1](https://benchize.com/models/gpt-4-1.md) | 36.48source score | CI 36.44–36.53 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 36.48357264 \| source_score \| reported \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration gpt-4.1 sourceModelVersion Not reported thinkingEnabled Not reported ### Reported statistics Uncertainty Confidence interval: 36.44–36.53 contaminationWarning Not reported rank 39 reportedConfidenceHalfWidth 0.04821631431 ### Source [Original source](https://labs.scale.com/leaderboard/prbench-legal) Source scale Original model label gpt-4.1 Observed 2026-10-21T16:35:35.197Z Evidence SHA-256 `9e2ca4e9350870cf508bf5fff603d0b795c81f7974a0ab980312bbbfa0785067` Source locator `/rows/38` | | | | | | 26 | [GPT-4.1 Mini](https://benchize.com/models/gpt-4-1-mini.md) | 30.38source score | CI 29.82–30.93 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 30.37525441 \| source_score \| reported \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration gpt-4.1-mini sourceModelVersion Not reported thinkingEnabled Not reported ### Reported statistics Uncertainty Confidence interval: 29.82–30.93 contaminationWarning Not reported rank 42 reportedConfidenceHalfWidth 0.552024228 ### Source [Original source](https://labs.scale.com/leaderboard/prbench-legal) Source scale Original model label gpt-4.1-mini Observed 2026-10-21T16:35:35.197Z Evidence SHA-256 `9e2ca4e9350870cf508bf5fff603d0b795c81f7974a0ab980312bbbfa0785067` Source locator `/rows/41` | | | | | --- Cite as: PRBench Legal — Benchize, https://benchize.com/benchmarks/scale%3Aprbench-legal (retrieved 2026-10-21)