pgai.MODEST PRAISE. PUBLIC NUMBERS.
← Back to the scoreboard

GPT-5.1 Thinking

Data as of 2026-10-14 / manually checked

4 models · 7 benchmarks · zero composite scores

pretty greatpretty okaynot yetTap a verdict for the number and source.
OpenAI

GPT-5.1 Thinking

Pretty great at coding, science.

SWE-bench Verified
pretty great
76.3%

Vendor-reported research evaluation, maximum available reasoning effort. See source for harness and sampling.

Source ↗Observed 2026-10-14
Terminal-Bench 2.0 not reported
ARC-AGI-2
not yet
17.6%

Vendor-reported research evaluation, maximum available reasoning effort. See source for harness and sampling.

Source ↗Observed 2026-10-14
GPQA Diamond
pretty great
88.1%

Vendor-reported research evaluation, maximum available reasoning effort. See source for harness and sampling.

Source ↗Observed 2026-10-14
AIME 2025
pretty okay
94%

Vendor-reported research evaluation, maximum available reasoning effort. See source for harness and sampling.

Source ↗Observed 2026-10-14
MRCRv2 · 128k–256k
not yet
29.6%

Vendor-reported research evaluation, maximum available reasoning effort. See source for harness and sampling.

Source ↗Observed 2026-10-14

The top score means the top sourced score in this snapshot. Different harnesses, budgets and samples can change results. A blank cell is a blank cell.

Verdict history

Each import keeps previous observations. Verdicts can also change when the comparison score changes.

SWE-bench Verifiedpretty great · 76.32026-10-15 14:06:27Source ↗
Terminal-Bench 2.0not reported · not reported2026-10-15 14:06:27
ARC-AGI-2not yet · 17.62026-10-15 14:06:27Source ↗
GPQA Diamondpretty great · 88.12026-10-15 14:06:27Source ↗
AIME 2025pretty okay · 942026-10-15 14:06:27Source ↗
LMArena / Text Arenanot reported · not reported2026-10-15 14:06:27
MRCRv2 · 128k–256knot yet · 29.62026-10-15 14:06:27Source ↗