PRBench Legal
SL · Professional reasoning · Rubric
Applied legal reasoning on professional-domain tasks.
Rank #31
verified runtimeexact direct
Raw row drilldownsource row, percentile, last updated, eligibility
- Source
- Scale Labs
- Raw value
- 38.6%
- Percentile
- 26.8%
- Last updated
- recent
- Eligibility
- headline eligible
Parsed from the public Scale Labs page for scale-prbench-legal. Reported model configuration: gpt-6-sol. Collapse policy: highest reported score per canonical model.
26.8% percentile inside its fair comparison set38.6%Raw benchmark value
Text Arena · Expert
AR · Professional reasoning · Human
Observed user preference in Arena's Text Arena expert leaderboard.
Rank #46 · Source label: gpt-6-sol-max
verified runtimeexact alias
Raw row drilldownsource row, percentile, last updated, eligibility
- Source
- Arena
- Raw value
- 1,498
- Percentile
- 86.2%
- Last updated
- aging
- Eligibility
- headline eligible
Parsed from Arena leaderboard dataset row `gpt-6-sol-max`. Category: expert. Source rank: #47. Votes: 918. Organization: openai. License: Proprietary.
86.2% percentile inside its fair comparison set1,498Raw benchmark valueCI 1,478 - 1,517
Text Arena · Industry Business And Management And Financial Operations
AR · Professional reasoning · Human
Observed user preference in Arena's Text Arena industry_business_and_management_and_financial_operations leaderboard.
Rank #78 · Source label: gpt-6-sol-max
verified runtimeexact alias
Raw row drilldownsource row, percentile, last updated, eligibility
- Source
- Arena
- Raw value
- 1,446
- Percentile
- 79.1%
- Last updated
- aging
- Eligibility
- headline eligible
Parsed from Arena leaderboard dataset row `gpt-6-sol-max`. Category: industry_business_and_management_and_financial_operations. Source rank: #86. Votes: 1662. Organization: openai. License: Proprietary.
79.1% percentile inside its fair comparison set1,446Raw benchmark valueCI 1,431 - 1,461
Text Arena · Industry Entertainment And Sports And Media
AR · Professional reasoning · Human
Observed user preference in Arena's Text Arena industry_entertainment_and_sports_and_media leaderboard.
Rank #46 · Source label: gpt-6-sol-max
verified runtimeexact alias
Raw row drilldownsource row, percentile, last updated, eligibility
- Source
- Arena
- Raw value
- 1,442
- Percentile
- 88%
- Last updated
- aging
- Eligibility
- headline eligible
Parsed from Arena leaderboard dataset row `gpt-6-sol-max`. Category: industry_entertainment_and_sports_and_media. Source rank: #49. Votes: 2138. Organization: openai. License: Proprietary.
88% percentile inside its fair comparison set1,442Raw benchmark valueCI 1,428 - 1,456
Text Arena · Industry Legal And Government
AR · Professional reasoning · Human
Observed user preference in Arena's Text Arena industry_legal_and_government leaderboard.
Rank #78 · Source label: gpt-6-sol-max
verified runtimeexact alias
Raw row drilldownsource row, percentile, last updated, eligibility
- Source
- Arena
- Raw value
- 1,453
- Percentile
- 77.9%
- Last updated
- aging
- Eligibility
- headline eligible
Parsed from Arena leaderboard dataset row `gpt-6-sol-max`. Category: industry_legal_and_government. Source rank: #88. Votes: 774. Organization: openai. License: Proprietary.
77.9% percentile inside its fair comparison set1,453Raw benchmark valueCI 1,432 - 1,475
Text Arena · Industry Life And Physical And Social Science
AR · Professional reasoning · Human
Observed user preference in Arena's Text Arena industry_life_and_physical_and_social_science leaderboard.
Rank #64 · Source label: gpt-6-sol-max
verified runtimeexact alias
Raw row drilldownsource row, percentile, last updated, eligibility
- Source
- Arena
- Raw value
- 1,473
- Percentile
- 83.2%
- Last updated
- aging
- Eligibility
- headline eligible
Parsed from Arena leaderboard dataset row `gpt-6-sol-max`. Category: industry_life_and_physical_and_social_science. Source rank: #71. Votes: 1469. Organization: openai. License: Proprietary.
83.2% percentile inside its fair comparison set1,473Raw benchmark valueCI 1,457 - 1,488
Text Arena · Industry Mathematical
AR · Professional reasoning · Human
Observed user preference in Arena's Text Arena industry_mathematical leaderboard.
Rank #72 · Source label: gpt-6-sol-max
verified runtimeexact alias
Raw row drilldownsource row, percentile, last updated, eligibility
- Source
- Arena
- Raw value
- 1,454
- Percentile
- 80.1%
- Last updated
- aging
- Eligibility
- headline eligible
Parsed from Arena leaderboard dataset row `gpt-6-sol-max`. Category: industry_mathematical. Source rank: #78. Votes: 537. Organization: openai. License: Proprietary.
80.1% percentile inside its fair comparison set1,454Raw benchmark valueCI 1,428 - 1,479
Text Arena · Industry Medicine And Healthcare
AR · Professional reasoning · Human
Observed user preference in Arena's Text Arena industry_medicine_and_healthcare leaderboard.
Rank #87 · Source label: gpt-6-sol-max
verified runtimeexact alias
Raw row drilldownsource row, percentile, last updated, eligibility
- Source
- Arena
- Raw value
- 1,458
- Percentile
- 75.1%
- Last updated
- aging
- Eligibility
- headline eligible
Parsed from Arena leaderboard dataset row `gpt-6-sol-max`. Category: industry_medicine_and_healthcare. Source rank: #98. Votes: 645. Organization: openai. License: Proprietary.
75.1% percentile inside its fair comparison set1,458Raw benchmark valueCI 1,433 - 1,483
Text Arena · Industry Software And It Services
AR · Professional reasoning · Human
Observed user preference in Arena's Text Arena industry_software_and_it_services leaderboard.
Rank #43 · Source label: gpt-6-sol-max
verified runtimeexact alias
Raw row drilldownsource row, percentile, last updated, eligibility
- Source
- Arena
- Raw value
- 1,505
- Percentile
- 88.8%
- Last updated
- aging
- Eligibility
- headline eligible
Parsed from Arena leaderboard dataset row `gpt-6-sol-max`. Category: industry_software_and_it_services. Source rank: #44. Votes: 3238. Organization: openai. License: Proprietary.
88.8% percentile inside its fair comparison set1,505Raw benchmark valueCI 1,494 - 1,516
Text Arena · Industry Writing And Literature And Language
AR · Professional reasoning · Human
Observed user preference in Arena's Text Arena industry_writing_and_literature_and_language leaderboard.
Rank #64 · Source label: gpt-6-sol-max
verified runtimeexact alias
Raw row drilldownsource row, percentile, last updated, eligibility
- Source
- Arena
- Raw value
- 1,439
- Percentile
- 83.2%
- Last updated
- aging
- Eligibility
- headline eligible
Parsed from Arena leaderboard dataset row `gpt-6-sol-max`. Category: industry_writing_and_literature_and_language. Source rank: #71. Votes: 2407. Organization: openai. License: Proprietary.
83.2% percentile inside its fair comparison set1,439Raw benchmark valueCI 1,426 - 1,451
Text Arena · Expert · No Style Control
AR · Professional reasoning · Human
Observed user preference in Arena's Text Arena expert leaderboard.
Rank #94 · Source label: gpt-6-sol-max
verified runtimeexact alias
Raw row drilldownsource row, percentile, last updated, eligibility
- Source
- Arena
- Raw value
- 1,439
- Percentile
- 71.6%
- Last updated
- aging
- Eligibility
- headline eligible
Parsed from Arena leaderboard dataset row `gpt-6-sol-max`. Category: expert. Source rank: #99. Votes: 918. Organization: openai. License: Proprietary.
71.6% percentile inside its fair comparison set1,439Raw benchmark valueCI 1,419 - 1,458
Text Arena · Industry Business And Management And Financial Operations · No Style Control
AR · Professional reasoning · Human
Observed user preference in Arena's Text Arena industry_business_and_management_and_financial_operations leaderboard.
Rank #150 · Source label: gpt-6-sol-max
verified runtimeexact alias
Raw row drilldownsource row, percentile, last updated, eligibility
- Source
- Arena
- Raw value
- 1,378
- Percentile
- 59.6%
- Last updated
- aging
- Eligibility
- headline eligible
Parsed from Arena leaderboard dataset row `gpt-6-sol-max`. Category: industry_business_and_management_and_financial_operations. Source rank: #166. Votes: 1662. Organization: openai. License: Proprietary.
59.6% percentile inside its fair comparison set1,378Raw benchmark valueCI 1,363 - 1,392
Text Arena · Industry Entertainment And Sports And Media · No Style Control
AR · Professional reasoning · Human
Observed user preference in Arena's Text Arena industry_entertainment_and_sports_and_media leaderboard.
Rank #113 · Source label: gpt-6-sol-max
verified runtimeexact alias
Raw row drilldownsource row, percentile, last updated, eligibility
- Source
- Arena
- Raw value
- 1,382
- Percentile
- 70.1%
- Last updated
- aging
- Eligibility
- headline eligible
Parsed from Arena leaderboard dataset row `gpt-6-sol-max`. Category: industry_entertainment_and_sports_and_media. Source rank: #123. Votes: 2138. Organization: openai. License: Proprietary.
70.1% percentile inside its fair comparison set1,382Raw benchmark valueCI 1,368 - 1,396
Text Arena · Industry Legal And Government · No Style Control
AR · Professional reasoning · Human
Observed user preference in Arena's Text Arena industry_legal_and_government leaderboard.
Rank #152 · Source label: gpt-6-sol-max
verified runtimeexact alias
Raw row drilldownsource row, percentile, last updated, eligibility
- Source
- Arena
- Raw value
- 1,386
- Percentile
- 56.7%
- Last updated
- aging
- Eligibility
- headline eligible
Parsed from Arena leaderboard dataset row `gpt-6-sol-max`. Category: industry_legal_and_government. Source rank: #169. Votes: 774. Organization: openai. License: Proprietary.
56.7% percentile inside its fair comparison set1,386Raw benchmark valueCI 1,364 - 1,407
Text Arena · Industry Life And Physical And Social Science · No Style Control
AR · Professional reasoning · Human
Observed user preference in Arena's Text Arena industry_life_and_physical_and_social_science leaderboard.
Rank #154 · Source label: gpt-6-sol-max
verified runtimeexact alias
Raw row drilldownsource row, percentile, last updated, eligibility
- Source
- Arena
- Raw value
- 1,387
- Percentile
- 59.1%
- Last updated
- aging
- Eligibility
- headline eligible
Parsed from Arena leaderboard dataset row `gpt-6-sol-max`. Category: industry_life_and_physical_and_social_science. Source rank: #170. Votes: 1469. Organization: openai. License: Proprietary.
59.1% percentile inside its fair comparison set1,387Raw benchmark valueCI 1,371 - 1,403
Text Arena · Industry Mathematical · No Style Control
AR · Professional reasoning · Human
Observed user preference in Arena's Text Arena industry_mathematical leaderboard.
Rank #131 · Source label: gpt-6-sol-max
verified runtimeexact alias
Raw row drilldownsource row, percentile, last updated, eligibility
- Source
- Arena
- Raw value
- 1,412
- Percentile
- 63.5%
- Last updated
- aging
- Eligibility
- headline eligible
Parsed from Arena leaderboard dataset row `gpt-6-sol-max`. Category: industry_mathematical. Source rank: #143. Votes: 537. Organization: openai. License: Proprietary.
63.5% percentile inside its fair comparison set1,412Raw benchmark valueCI 1,386 - 1,437
Text Arena · Industry Medicine And Healthcare · No Style Control
AR · Professional reasoning · Human
Observed user preference in Arena's Text Arena industry_medicine_and_healthcare leaderboard.
Rank #173 · Source label: gpt-6-sol-max
verified runtimeexact alias
Raw row drilldownsource row, percentile, last updated, eligibility
- Source
- Arena
- Raw value
- 1,362
- Percentile
- 50.3%
- Last updated
- aging
- Eligibility
- headline eligible
Parsed from Arena leaderboard dataset row `gpt-6-sol-max`. Category: industry_medicine_and_healthcare. Source rank: #193. Votes: 645. Organization: openai. License: Proprietary.
50.3% percentile inside its fair comparison set1,362Raw benchmark valueCI 1,338 - 1,387
Text Arena · Industry Software And It Services · No Style Control
AR · Professional reasoning · Human
Observed user preference in Arena's Text Arena industry_software_and_it_services leaderboard.
Rank #120 · Source label: gpt-6-sol-max
verified runtimeexact alias
Raw row drilldownsource row, percentile, last updated, eligibility
- Source
- Arena
- Raw value
- 1,432
- Percentile
- 68.4%
- Last updated
- aging
- Eligibility
- headline eligible
Parsed from Arena leaderboard dataset row `gpt-6-sol-max`. Category: industry_software_and_it_services. Source rank: #132. Votes: 3238. Organization: openai. License: Proprietary.
68.4% percentile inside its fair comparison set1,432Raw benchmark valueCI 1,421 - 1,442
Text Arena · Industry Writing And Literature And Language · No Style Control
AR · Professional reasoning · Human
Observed user preference in Arena's Text Arena industry_writing_and_literature_and_language leaderboard.
Rank #118 · Source label: gpt-6-sol-max
verified runtimeexact alias
Raw row drilldownsource row, percentile, last updated, eligibility
- Source
- Arena
- Raw value
- 1,390
- Percentile
- 68.8%
- Last updated
- aging
- Eligibility
- headline eligible
Parsed from Arena leaderboard dataset row `gpt-6-sol-max`. Category: industry_writing_and_literature_and_language. Source rank: #130. Votes: 2407. Organization: openai. License: Proprietary.
68.8% percentile inside its fair comparison set1,390Raw benchmark valueCI 1,377 - 1,403
Vals Index
VALS-AI · Professional reasoning · Combined
Weighted model performance across economically relevant Vals tasks.
Rank #11 · Source label: openai/gpt-6-sol
verified runtimeexact alias
Raw row drilldownsource row, percentile, last updated, eligibility
- Source
- Vals AI
- Raw value
- 58
- Percentile
- 75%
- Last updated
- aging
- Eligibility
- headline eligible
Parsed from Vals AI BenchmarkView overall scores. Vals slug: vals_index; provider: OpenAI.
75% percentile inside its fair comparison set58Raw benchmark valueCI 56 - 60
Legal Research Bench
VALS-AI · Professional reasoning · Objective
Applied legal research tasks.
Rank #41 · Source label: openai/gpt-6-sol
verified runtimeexact alias
Raw row drilldownsource row, percentile, last updated, eligibility
- Source
- Vals AI
- Raw value
- 28.8%
- Percentile
- 41.2%
- Last updated
- aging
- Eligibility
- headline eligible
Parsed from Vals AI BenchmarkView overall scores. Vals slug: legal_research; provider: OpenAI.
41.2% percentile inside its fair comparison set28.8%Raw benchmark valueCI 22.7% - 35%
Harvey's Legal Agent Benchmark
VALS-AI · Professional reasoning · Objective
Completing legal work with documents, spreadsheets, presentations, and file-system tools.
Rank #44 · Source label: openai/gpt-6-sol
verified runtimeexact alias
Raw row drilldownsource row, percentile, last updated, eligibility
- Source
- Vals AI
- Raw value
- 1.7%
- Percentile
- 39.1%
- Last updated
- aging
- Eligibility
- headline eligible
Parsed from Vals AI BenchmarkView overall scores. Vals slug: hlab; provider: OpenAI.
39.1% percentile inside its fair comparison set1.7%Raw benchmark valueCI 0.1% - 3.3%
Finance Agent v2
VALS-AI · Professional reasoning · Objective
Core financial analyst tasks for agentic models.
Rank #39 · Source label: openai/gpt-6-sol
verified runtimeexact alias
Raw row drilldownsource row, percentile, last updated, eligibility
- Source
- Vals AI
- Raw value
- 49.1%
- Percentile
- 44.9%
- Last updated
- aging
- Eligibility
- headline eligible
Parsed from Vals AI BenchmarkView overall scores. Vals slug: fabv2; provider: OpenAI.
44.9% percentile inside its fair comparison set49.1%Raw benchmark valueCI 47.9% - 50.2%
MedCode
VALS-AI · Professional reasoning · Objective
Medical billing support and coding tasks.
Rank #34 · Source label: openai/gpt-6-sol
verified runtimeexact alias
Raw row drilldownsource row, percentile, last updated, eligibility
- Source
- Vals AI
- Raw value
- 47.1%
- Percentile
- 65.3%
- Last updated
- aging
- Eligibility
- headline eligible
Parsed from Vals AI BenchmarkView overall scores. Vals slug: medcode; provider: OpenAI.
65.3% percentile inside its fair comparison set47.1%Raw benchmark valueCI 42.9% - 51.2%
MedScribe
VALS-AI · Professional reasoning · Objective
Administrative documentation support for doctors.
Rank #49 · Source label: openai/gpt-6-sol
verified runtimeexact alias
Raw row drilldownsource row, percentile, last updated, eligibility
- Source
- Vals AI
- Raw value
- 82%
- Percentile
- 50%
- Last updated
- aging
- Eligibility
- headline eligible
Parsed from Vals AI BenchmarkView overall scores. Vals slug: medscribe; provider: OpenAI.
50% percentile inside its fair comparison set82%Raw benchmark valueCI 78.2% - 85.8%
SAGE
VALS-AI · Professional reasoning · Objective
Student Assessment with Generative Evaluation.
Rank #43 · Source label: openai/gpt-6-sol
verified runtimeexact alias
Raw row drilldownsource row, percentile, last updated, eligibility
- Source
- Vals AI
- Raw value
- 44.8%
- Percentile
- 48.1%
- Last updated
- aging
- Eligibility
- headline eligible
Parsed from Vals AI BenchmarkView overall scores. Vals slug: sage; provider: OpenAI.
48.1% percentile inside its fair comparison set44.8%Raw benchmark valueCI 38.2% - 51.4%
Public Benefits Bench
VALS-AI · Professional reasoning · Objective
Answering SNAP benefits questions across the public-benefits lifecycle.
Rank #36 · Source label: openai/gpt-6-sol
verified runtimeexact alias
Raw row drilldownsource row, percentile, last updated, eligibility
- Source
- Vals AI
- Raw value
- 56.6%
- Percentile
- 24.4%
- Last updated
- aging
- Eligibility
- headline eligible
Parsed from Vals AI BenchmarkView overall scores. Vals slug: public-benefits-bench; provider: OpenAI.
24.4% percentile inside its fair comparison set56.6%Raw benchmark valueCI 54.1% - 59.2%
Data analysis
LB · Professional reasoning · Objective
Structured data manipulation and table reasoning accuracy.
Rank #5 · Source label: gpt-6-sol-max
verified runtimeexact alias
Raw row drilldownsource row, percentile, last updated, eligibility
- Source
- LiveBench
- Raw value
- 81.2%
- Percentile
- 93.9%
- Last updated
- archived
- Eligibility
- headline eligible
Derived from the official LiveBench website leaderboard table. Category: Data Analysis. Tasks scored: 3.
93.9% percentile inside its fair comparison set81.2%Raw benchmark value
Overall
LB · Professional reasoning · Objective
Average objective performance across LiveBench's current public category mix.
Rank #14 · Source label: gpt-6-sol-max
verified runtimeexact alias
Raw row drilldownsource row, percentile, last updated, eligibility
- Source
- LiveBench
- Raw value
- 79.2%
- Percentile
- 80.3%
- Last updated
- archived
- Eligibility
- headline eligible
Derived from the official LiveBench website leaderboard table. Category averages included: 7.
80.3% percentile inside its fair comparison set79.2%Raw benchmark value
Consecutive events
LB · Professional reasoning · Objective
Objective consecutive events score in LiveBench.
Rank #16 · Source label: gpt-6-sol-max
verified runtimeexact alias
Raw row drilldownsource row, percentile, last updated, eligibility
- Source
- LiveBench
- Raw value
- 89.5%
- Percentile
- 77.3%
- Last updated
- archived
- Eligibility
- headline eligible
Derived from the official LiveBench website leaderboard table. Task: consecutive_events. Category: Data Analysis.
77.3% percentile inside its fair comparison set89.5%Raw benchmark value
Table join
LB · Professional reasoning · Objective
Objective table join score in LiveBench.
Rank #7 · Source label: gpt-6-sol-max
verified runtimeexact alias
Raw row drilldownsource row, percentile, last updated, eligibility
- Source
- LiveBench
- Raw value
- 54%
- Percentile
- 90.9%
- Last updated
- archived
- Eligibility
- headline eligible
Derived from the official LiveBench website leaderboard table. Task: tablejoin. Category: Data Analysis.
90.9% percentile inside its fair comparison set54%Raw benchmark value
Table reformat
LB · Professional reasoning · Objective
Objective table reformat score in LiveBench.
Rank #22 · Source label: gpt-6-sol-max
verified runtimeexact alias
Raw row drilldownsource row, percentile, last updated, eligibility
- Source
- LiveBench
- Raw value
- 100%
- Percentile
- 100%
- Last updated
- archived
- Eligibility
- headline eligible
Derived from the official LiveBench website leaderboard table. Task: tablereformat. Category: Data Analysis.
100% percentile inside its fair comparison set100%Raw benchmark value