Model results
DrivingBench
Choose a shared evaluation protocol to compare model scores. Versions, sources and configurations stay separate.
Atlas snapshot captured 10/19/2026, 10:20:28 AM UTC. This is an import timestamp, not the evaluation date. Coverage may be incomplete.
Evaluation groups
Open a group to see its exact protocol and scores. Different configurations remain separate.
No model rankings are available in this snapshot. Reported results remain available below.
Other reported results
These reports have no model ranking. Open a group for its evidence and the reason positions are withheld.
- Claude Fable 5.12026-09-v1-cone-course-best-of-3
DrivingBench · DrivingBench (reviewed publisher results)
Single-model result · Positions withheld
Measurement date not reported
Scope · Best progress of up to 3 attempts in one continuous chat; 45% along the course centerline within 4 m…
Best progress of up to 3 attempts in one continuous chat; 45% along the course centerline within 4 m; attempt 3 reached 45% (attempts 1–2: 9%, 10%), DNF; harness=Claude Code, reasoning=medium; real 2022 Toyota Corolla via comma four and openpilot, three MCP tools (observe, set_motion, stop_now), human on the brake; single physical run per attempt, not a repeated-trial success rate; result date not supplied; captured 2026-09-23.
- GPT-5.6 Sol2026-09-v1-cone-course-best-of-3
DrivingBench · DrivingBench (reviewed publisher results)
Single-model result · Positions withheld
Measurement date not reported
Scope · Best progress of up to 3 attempts in one continuous chat; 6% along the course centerline within 4 m;…
Best progress of up to 3 attempts in one continuous chat; 6% along the course centerline within 4 m; 6% on all three attempts, DNF; harness=Codex, reasoning=medium; real 2022 Toyota Corolla via comma four and openpilot, three MCP tools (observe, set_motion, stop_now), human on the brake; single physical run per attempt, not a repeated-trial success rate; result date not supplied; captured 2026-09-23.
- GPT-6 Astra2026-09-v1-cone-course-best-of-3
DrivingBench · DrivingBench (reviewed publisher results)
Single-model result · Positions withheld
Measurement date not reported
Scope · Best progress of up to 3 attempts in one continuous chat; 100% along the course centerline within 4 …
Best progress of up to 3 attempts in one continuous chat; 100% along the course centerline within 4 m; only model to finish the course, attempt 2 in 5:22 (attempt 1 49%); harness=Codex, reasoning=medium; real 2022 Toyota Corolla via comma four and openpilot, three MCP tools (observe, set_motion, stop_now), human on the brake; single physical run per attempt, not a repeated-trial success rate; result date not supplied; captured 2026-09-23.
- Grok 4.62026-09-v1-cone-course-best-of-3
DrivingBench · DrivingBench (reviewed publisher results)
Single-model result · Positions withheld
Measurement date not reported
Scope · Best progress of up to 3 attempts in one continuous chat; 11% along the course centerline within 4 m…
Best progress of up to 3 attempts in one continuous chat; 11% along the course centerline within 4 m; attempt 2 reached 11% (attempts 1, 3: 8%, 10%), DNF; harness=Cursor, reasoning=medium; real 2022 Toyota Corolla via comma four and openpilot, three MCP tools (observe, set_motion, stop_now), human on the brake; single physical run per attempt, not a repeated-trial success rate; result date not supplied; captured 2026-09-23.