Name: GPT-5.6 Sol vs GPT-6 Sol
Creator: Benchmark Registry

Shared benchmarks

Shared benchmarks for GPT-5.6 Sol and GPT-6 Sol
Benchmark	GPT-5.6 Sol	GPT-6 Sol
AutomationBench 1.0.6	28.8%1.0.6 · Task pass rate OpenAI 19.6%1.0.6 · Task pass rate OpenAI 24.8%1.0.6 · Task pass rate OpenAI 26.3%1.0.6 · Task pass rate OpenAI 11.7%1.0.6 · Task pass rate OpenAI	26.9%1.0.6 · Task pass rate OpenAI 32.0%1.0.6 · Task pass rate OpenAI 21.2%1.0.6 · Task pass rate OpenAI 31.2%1.0.6 · Task pass rate OpenAI 33.2%1.0.6 · Task pass rate OpenAI
Evaluation details for AutomationBench 1.0.6 The recorded benchmark version, metric, and evaluator sets match. Evaluation methodology is not recorded by the registry. GPT-5.6 Sol Score 28.8% Evaluator OpenAI Version AutomationBench 1.0.6 Metric Task pass rate (percent) Reasoning max Reported September 22, 2026 Source Evaluation source for GPT-5.6 Sol on AutomationBench 1.0.6 (opens in a new tab) Score 19.6% Evaluator OpenAI Version AutomationBench 1.0.6 Metric Task pass rate (percent) Reasoning medium Reported September 22, 2026 Source Evaluation source for GPT-5.6 Sol on AutomationBench 1.0.6 (opens in a new tab) Score 24.8% Evaluator OpenAI Version AutomationBench 1.0.6 Metric Task pass rate (percent) Reasoning high Reported September 22, 2026 Source Evaluation source for GPT-5.6 Sol on AutomationBench 1.0.6 (opens in a new tab) Score 26.3% Evaluator OpenAI Version AutomationBench 1.0.6 Metric Task pass rate (percent) Reasoning xhigh Reported September 22, 2026 Source Evaluation source for GPT-5.6 Sol on AutomationBench 1.0.6 (opens in a new tab) Score 11.7% Evaluator OpenAI Version AutomationBench 1.0.6 Metric Task pass rate (percent) Reasoning low Reported September 22, 2026 Source Evaluation source for GPT-5.6 Sol on AutomationBench 1.0.6 (opens in a new tab) GPT-6 Sol Score 26.9% Evaluator OpenAI Version AutomationBench 1.0.6 Metric Task pass rate (percent) Reasoning medium Reported September 22, 2026 Source Evaluation source for GPT-6 Sol on AutomationBench 1.0.6 (opens in a new tab) Score 32.0% Evaluator OpenAI Version AutomationBench 1.0.6 Metric Task pass rate (percent) Reasoning max Reported September 22, 2026 Source Evaluation source for GPT-6 Sol on AutomationBench 1.0.6 (opens in a new tab) Score 21.2% Evaluator OpenAI Version AutomationBench 1.0.6 Metric Task pass rate (percent) Reasoning low Reported September 22, 2026 Source Evaluation source for GPT-6 Sol on AutomationBench 1.0.6 (opens in a new tab) Score 31.2% Evaluator OpenAI Version AutomationBench 1.0.6 Metric Task pass rate (percent) Reasoning high Reported September 22, 2026 Source Evaluation source for GPT-6 Sol on AutomationBench 1.0.6 (opens in a new tab) Score 33.2% Evaluator OpenAI Version AutomationBench 1.0.6 Metric Task pass rate (percent) Reasoning xhigh Reported September 22, 2026 Source Evaluation source for GPT-6 Sol on AutomationBench 1.0.6 (opens in a new tab)
DeepSWE 1.1Potentially non-equivalent: Evaluator sets differ.	73.0%1.1 · DeepSWE Pass@1 DataCurve 70.7%1.1 · DeepSWE Pass@1 OpenAI 72.7%1.1 · DeepSWE Pass@1 OpenAI 61.1%1.1 · DeepSWE Pass@1 OpenAI 69.4%1.1 · DeepSWE Pass@1 OpenAI 45.4%1.1 · DeepSWE Pass@1 OpenAI	66.6%1.1 · DeepSWE Pass@1 OpenAI 56.6%1.1 · DeepSWE Pass@1 OpenAI 68.8%1.1 · DeepSWE Pass@1 OpenAI 37.2%1.1 · DeepSWE Pass@1 OpenAI 65.3%1.1 · DeepSWE Pass@1 OpenAI
Potentially non-equivalent · Evaluation details for DeepSWE 1.1 Evaluator sets differ. Evaluation methodology is not recorded by the registry. GPT-5.6 Sol Score 73.0% Evaluator DataCurve Version DeepSWE 1.1 Metric DeepSWE Pass@1 (percent) Reasoning max Reported September 22, 2026 Source Evaluation source for GPT-5.6 Sol on DeepSWE 1.1 (opens in a new tab) Score 70.7% Evaluator OpenAI Version DeepSWE 1.1 Metric DeepSWE Pass@1 (percent) Reasoning xhigh Reported September 22, 2026 Source Evaluation source for GPT-5.6 Sol on DeepSWE 1.1 (opens in a new tab) Score 72.7% Evaluator OpenAI Version DeepSWE 1.1 Metric DeepSWE Pass@1 (percent) Reasoning Not specified Reported July 9, 2026 Source Evaluation source for GPT-5.6 Sol on DeepSWE 1.1 (opens in a new tab) Score 61.1% Evaluator OpenAI Version DeepSWE 1.1 Metric DeepSWE Pass@1 (percent) Reasoning medium Reported September 22, 2026 Source Evaluation source for GPT-5.6 Sol on DeepSWE 1.1 (opens in a new tab) Score 69.4% Evaluator OpenAI Version DeepSWE 1.1 Metric DeepSWE Pass@1 (percent) Reasoning high Reported September 22, 2026 Source Evaluation source for GPT-5.6 Sol on DeepSWE 1.1 (opens in a new tab) Score 45.4% Evaluator OpenAI Version DeepSWE 1.1 Metric DeepSWE Pass@1 (percent) Reasoning low Reported September 22, 2026 Source Evaluation source for GPT-5.6 Sol on DeepSWE 1.1 (opens in a new tab) GPT-6 Sol Score 66.6% Evaluator OpenAI Version DeepSWE 1.1 Metric DeepSWE Pass@1 (percent) Reasoning xhigh Reported September 22, 2026 Source Evaluation source for GPT-6 Sol on DeepSWE 1.1 (opens in a new tab) Score 56.6% Evaluator OpenAI Version DeepSWE 1.1 Metric DeepSWE Pass@1 (percent) Reasoning medium Reported September 22, 2026 Source Evaluation source for GPT-6 Sol on DeepSWE 1.1 (opens in a new tab) Score 68.8% Evaluator OpenAI Version DeepSWE 1.1 Metric DeepSWE Pass@1 (percent) Reasoning max Reported September 22, 2026 Source Evaluation source for GPT-6 Sol on DeepSWE 1.1 (opens in a new tab) Score 37.2% Evaluator OpenAI Version DeepSWE 1.1 Metric DeepSWE Pass@1 (percent) Reasoning low Reported September 22, 2026 Source Evaluation source for GPT-6 Sol on DeepSWE 1.1 (opens in a new tab) Score 65.3% Evaluator OpenAI Version DeepSWE 1.1 Metric DeepSWE Pass@1 (percent) Reasoning high Reported September 22, 2026 Source Evaluation source for GPT-6 Sol on DeepSWE 1.1 (opens in a new tab)
OSWorld 2.0 v2026.08.08 Offline — Partial	56.5%2.0 v2026.08.08 Offline — Partial · OSWorld Partial Score OpenAI 66.2%2.0 v2026.08.08 Offline — Partial · OSWorld Partial Score OpenAI 29.8%2.0 v2026.08.08 Offline — Partial · OSWorld Partial Score OpenAI 49.7%2.0 v2026.08.08 Offline — Partial · OSWorld Partial Score OpenAI 60.9%2.0 v2026.08.08 Offline — Partial · OSWorld Partial Score OpenAI	60.5%2.0 v2026.08.08 Offline — Partial · OSWorld Partial Score OpenAI 64.4%2.0 v2026.08.08 Offline — Partial · OSWorld Partial Score OpenAI 54.0%2.0 v2026.08.08 Offline — Partial · OSWorld Partial Score OpenAI 58.3%2.0 v2026.08.08 Offline — Partial · OSWorld Partial Score OpenAI 43.9%2.0 v2026.08.08 Offline — Partial · OSWorld Partial Score OpenAI
Evaluation details for OSWorld 2.0 v2026.08.08 Offline — Partial The recorded benchmark version, metric, and evaluator sets match. Evaluation methodology is not recorded by the registry. GPT-5.6 Sol Score 56.5% Evaluator OpenAI Version OSWorld 2.0 v2026.08.08 Offline — Partial Metric OSWorld Partial Score (percent) Reasoning high Reported September 22, 2026 Source Evaluation source for GPT-5.6 Sol on OSWorld 2.0 v2026.08.08 Offline — Partial (opens in a new tab) Score 66.2% Evaluator OpenAI Version OSWorld 2.0 v2026.08.08 Offline — Partial Metric OSWorld Partial Score (percent) Reasoning max Reported September 22, 2026 Source Evaluation source for GPT-5.6 Sol on OSWorld 2.0 v2026.08.08 Offline — Partial (opens in a new tab) Score 29.8% Evaluator OpenAI Version OSWorld 2.0 v2026.08.08 Offline — Partial Metric OSWorld Partial Score (percent) Reasoning low Reported September 22, 2026 Source Evaluation source for GPT-5.6 Sol on OSWorld 2.0 v2026.08.08 Offline — Partial (opens in a new tab) Score 49.7% Evaluator OpenAI Version OSWorld 2.0 v2026.08.08 Offline — Partial Metric OSWorld Partial Score (percent) Reasoning medium Reported September 22, 2026 Source Evaluation source for GPT-5.6 Sol on OSWorld 2.0 v2026.08.08 Offline — Partial (opens in a new tab) Score 60.9% Evaluator OpenAI Version OSWorld 2.0 v2026.08.08 Offline — Partial Metric OSWorld Partial Score (percent) Reasoning xhigh Reported September 22, 2026 Source Evaluation source for GPT-5.6 Sol on OSWorld 2.0 v2026.08.08 Offline — Partial (opens in a new tab) GPT-6 Sol Score 60.5% Evaluator OpenAI Version OSWorld 2.0 v2026.08.08 Offline — Partial Metric OSWorld Partial Score (percent) Reasoning xhigh Reported September 22, 2026 Source Evaluation source for GPT-6 Sol on OSWorld 2.0 v2026.08.08 Offline — Partial (opens in a new tab) Score 64.4% Evaluator OpenAI Version OSWorld 2.0 v2026.08.08 Offline — Partial Metric OSWorld Partial Score (percent) Reasoning max Reported September 22, 2026 Source Evaluation source for GPT-6 Sol on OSWorld 2.0 v2026.08.08 Offline — Partial (opens in a new tab) Score 54.0% Evaluator OpenAI Version OSWorld 2.0 v2026.08.08 Offline — Partial Metric OSWorld Partial Score (percent) Reasoning medium Reported September 22, 2026 Source Evaluation source for GPT-6 Sol on OSWorld 2.0 v2026.08.08 Offline — Partial (opens in a new tab) Score 58.3% Evaluator OpenAI Version OSWorld 2.0 v2026.08.08 Offline — Partial Metric OSWorld Partial Score (percent) Reasoning high Reported September 22, 2026 Source Evaluation source for GPT-6 Sol on OSWorld 2.0 v2026.08.08 Offline — Partial (opens in a new tab) Score 43.9% Evaluator OpenAI Version OSWorld 2.0 v2026.08.08 Offline — Partial Metric OSWorld Partial Score (percent) Reasoning low Reported September 22, 2026 Source Evaluation source for GPT-6 Sol on OSWorld 2.0 v2026.08.08 Offline — Partial (opens in a new tab)