Filled points are supported; hollow points are preliminary. Lines stop at unknown capabilities. Exact values and sources follow below.
Agentic1 families · 1 with independent evidence · Preliminary0.8
1 core families; 5 direct opponents across 2 labs. Needs broader benchmark and opponent support
Estimated against the same complete panel: gpt-5.6-sol claude-opus-4-8 gemini-3.1-pro . Indirect comparisons assume performance can be summarized by one strength within this capability.
Refit without one family: No supported estimate; 13/13 scenarios unsupported. Without one publisher: No supported estimate; 15/15 unsupported. Smoothing check: No supported estimate; 3/3 unsupported. These are sensitivity checks, not confidence intervals.
Audit: family and publisher holdouts improved on neutral predictions within evaluated coverage; source sensitivity still requires inspection. Validation audit.
Matched family win shares below describe source evidence; they are not averaged to produce the adjusted score.
- OSWorld: 0.0 observed win share
os-world.github.io · Source 1
Hard reasoning1 families · 1 with independent evidence · Preliminary18.4
1 core families; 59 direct opponents across 10 labs. Needs broader benchmark and opponent support
Estimated against the same complete panel: gpt-5.6-sol claude-opus-4-8 gemini-3.1-pro . Indirect comparisons assume performance can be summarized by one strength within this capability.
Refit without one family: No supported estimate; 6/6 scenarios unsupported. Without one publisher: No supported estimate; 16/16 unsupported. Smoothing check: No supported estimate; 3/3 unsupported. These are sensitivity checks, not confidence intervals.
Audit: family and publisher holdouts improved on neutral predictions within evaluated coverage. Validation audit.
Matched family win shares below describe source evidence; they are not averaged to produce the adjusted score.
- ARC-AGI: 32.2 observed win share
arcprize.org · Source 1
Coding2 families · 2 with independent evidence · Supported0.5
2 core families; 25 direct opponents across 10 labs.
Estimated against the same complete panel: gpt-5.6-sol claude-opus-4-8 gemini-3.1-pro . Indirect comparisons assume performance can be summarized by one strength within this capability.
Refit without one family: 0.2–2.6; 2/6 scenarios unsupported. Without one publisher: 0.3–2.3; 2/19 unsupported. Smoothing check: 0.1–2.9; 0/3 unsupported. These are sensitivity checks, not confidence intervals.
Audit: family and publisher holdouts improved on neutral predictions within evaluated coverage. Validation audit.
Matched family win shares below describe source evidence; they are not averaged to produce the adjusted score.
- SWE-bench Verified: 50.0 observed win share
swebench.com · Source 1 - LiveCodeBench: 87.5 observed win share
livecodebench.github.io · Source 1
Human prefNo comparable evidenceUnknown
0 core families; 0 direct opponents across 0 labs. No admitted core comparisons
Estimated against the same complete panel: gpt-5.6-sol claude-opus-4-8 gemini-3.1-pro . Indirect comparisons assume performance can be summarized by one strength within this capability.
Refit without one family: No supported estimate; 1/1 scenarios unsupported. Without one publisher: No supported estimate; 1/1 unsupported. Smoothing check: No supported estimate; 3/3 unsupported. These are sensitivity checks, not confidence intervals.
Audit: cross-family and cross-publisher predictions could not be evaluated from the available comparison network. Validation audit.
Matched family win shares below describe source evidence; they are not averaged to produce the adjusted score.
KnowledgeNo comparable evidenceUnknown
0 core families; 0 direct opponents across 0 labs. No admitted core comparisons
Estimated against the same complete panel: gpt-5.6-sol claude-opus-4-8 gemini-3.1-pro . Indirect comparisons assume performance can be summarized by one strength within this capability.
Refit without one family: No supported estimate; 4/4 scenarios unsupported. Without one publisher: No supported estimate; 5/5 unsupported. Smoothing check: No supported estimate; 3/3 unsupported. These are sensitivity checks, not confidence intervals.
Audit: almost no publisher-held-out comparisons remained estimable. Cross-source validity is unresolved. Validation audit.
Matched family win shares below describe source evidence; they are not averaged to produce the adjusted score.
MultimodalNo comparable evidenceUnknown
0 core families; 0 direct opponents across 0 labs. No admitted core comparisons
Estimated against the same complete panel: gpt-5.6-sol claude-opus-4-8 gemini-3.1-pro . Indirect comparisons assume performance can be summarized by one strength within this capability.
Refit without one family: No supported estimate; 8/8 scenarios unsupported. Without one publisher: No supported estimate; 8/8 unsupported. Smoothing check: No supported estimate; 3/3 unsupported. These are sensitivity checks, not confidence intervals.
Audit: limited publisher-held-out coverage. Cross-source validity is unresolved. Validation audit.
Matched family win shares below describe source evidence; they are not averaged to produce the adjusted score.
Long contextNo comparable evidenceUnknown
0 core families; 0 direct opponents across 0 labs. No admitted core comparisons
Estimated against the same complete panel: gpt-5.6-sol claude-opus-4-8 gemini-3.1-pro . Indirect comparisons assume performance can be summarized by one strength within this capability.
Refit without one family: No supported estimate; 5/5 scenarios unsupported. Without one publisher: No supported estimate; 5/5 unsupported. Smoothing check: No supported estimate; 3/3 unsupported. These are sensitivity checks, not confidence intervals.
Audit: family and publisher holdouts underperformed neutral predictions. Treat this as an exploratory estimate. Validation audit.
Matched family win shares below describe source evidence; they are not averaged to produce the adjusted score.
Scores estimate outcomes against a shared reference panel; they are not accuracy percentages. Sparse or disconnected evidence cannot qualify an overall profile. Open a capability to inspect its evidence.
/badge/o3.svg