# GPT-5.6 SolHigh

> Source: Benchize (https://benchize.com) — https://benchize.com/models/gpt-5-6-sol-high. When citing or reusing this content, credit "Benchize" and link to https://benchize.com/models/gpt-5-6-sol-high.

OpenAI

Canonical URL: https://benchize.com/models/gpt-5-6-sol-high
Last updated: Thu, 22 Oct 2026 07:10:12 GMT

Reproduction and quotation must name Benchize, link to the canonical HTML URL, and retain individual source citations.

OpenAI

## Benchmarks

| Benchmark | Score | ± | Rank | Cost | Latency | Source |  |
| --- | --- | --- | --- | --- | --- | --- | --- |
| [ARC-AGI-1](https://benchize.com/benchmarks/arc-prize%3Av1_Semi_Private.md) | 97% | — | 22 / 245 | 0.3usd per task | — | [arc prize · v1](https://arcprize.org/media/data/leaderboard/v1.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.97 \| score_fraction \| v1_Semi_Private \| Higher is better \| \| `cost_per_task` \| 0.3 \| usd_per_task \| v1_Semi_Private \| Lower is better \| ### Configuration evaluationSplit v1_Semi_Private harness Not reported modelGroup openai-gpt-5-6-sol modelType CoT Reasoning effort high sourceModelVersion openai-gpt-5-6-sol-high thinkingEnabled true ### Source [Original source](https://arcprize.org/media/data/leaderboard/v1.json) Source arc prize Original model label GPT-5.6 Sol (High) Source version v1 Observed 2026-10-22T05:20:04.066Z Evidence SHA-256 `2bf68d22dafba37047d07ad833ebc0e8199c9aa2f9eeaed50c75c1b704462836` Source locator `/evaluations/156` |  |  |  |  |  |  |  |
| [MirrorCode](https://benchize.com/benchmarks/epoch-ai%3Amirrorcode.md) | 20% | SE ±9.23 pp | 7 / 9 | — | — | [epoch ai · MirrorCode](https://epoch.ai/data/benchmark_data.zip#file=mirrorcode.csv) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.2 \| score_fraction \| Best score (across scorers) \| Higher is better \| \| `mean_score` \| 0.2 \| score_fraction \| mean_score \| Higher is better \| ### Configuration benchmarkVersion MirrorCode reasoningBudget Not reported Reasoning effort high sourceModelVersion gpt-5.6-sol_high ### Reported statistics Uncertainty Standard error: ±9.23 pp standardError 0.09229582069908972 ### Source [Original source](https://epoch.ai/data/benchmark_data.zip#file=mirrorcode.csv) Source epoch ai Original model label gpt-5.6-sol Source version MirrorCode Evaluated 2026-08-10T16:12:44.772Z Observed 2026-10-22T03:00:05.281Z Evidence SHA-256 `34012d7fe817c85c7baeba0e236d8c163dda4de486cc9d1f5a29c5b6d3196cd9` Source locator `/rows/8` |  |  |  |  |  |  |  |
| [DeepSWE](https://benchize.com/benchmarks/deepswe%3Av1.1.md) | 69.4% | Range 67.97–70.83% | 15 / 70 | $3.47 | 594.23s | [deepswe](https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `pass_at_1` \| 0.6940133037694013 \| score_fraction \| scored_rollout_attempts \| Higher is better \| \| `pass_at_4` \| 0.8672566371681416 \| score_fraction \| tasks_with_one_passing_rollout \| Higher is better \| \| `cost_per_attempt` \| 3.4698331108647453 \| USD \| scored_attempt \| Lower is better \| \| `duration` \| 594.230510789357 \| seconds \| scored_attempt \| Lower is better \| ### Configuration harness mini-swe-agent Reasoning effort high sourceConfiguration mini_swe_agent_gpt_5_6_sol_high ### Reported statistics Uncertainty Reported interval: 67.97–70.83% interval [0.679691851565629,0.7083347559731736] intervalMethod 95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R)) runCount 4 sampleSize 451 taskCount 113 ### Source [Original source](https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json) Source deepswe Original model label gpt-5-6-sol Observed 2026-10-22T03:50:05.889Z Evidence SHA-256 `a7c15d66288fd249c020b9931c017b92d1a3b90e480b3ff34974b752bd030019` Source locator `/rows/14` |  |  |  |  |  |  |  |
| [ARC-AGI-2](https://benchize.com/benchmarks/arc-prize%3Av2_Semi_Private.md) | 85.42% | — | 28 / 243 | 0.74usd per task | — | [arc prize · v2](https://arcprize.org/media/data/leaderboard/v2.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.8542 \| score_fraction \| v2_Semi_Private \| Higher is better \| \| `cost_per_task` \| 0.74 \| usd_per_task \| v2_Semi_Private \| Lower is better \| ### Configuration evaluationSplit v2_Semi_Private harness Not reported modelGroup openai-gpt-5-6-sol modelType CoT Reasoning effort high sourceModelVersion openai-gpt-5-6-sol-high thinkingEnabled true ### Source [Original source](https://arcprize.org/media/data/leaderboard/v2.json) Source arc prize Original model label GPT-5.6 Sol (High) Source version v2 Observed 2026-10-22T05:20:04.306Z Evidence SHA-256 `4351eb696e78113b0459e9bb5f0258318b905efef34f473dcea51ce641b0d94d` Source locator `/evaluations/157` |  |  |  |  |  |  |  |
| [AutomationBench](https://benchize.com/benchmarks/zapier%3Aautomationbench.md) | 24.81% | — | 28 / 113 | $0.64 | — | [zapier](https://framerusercontent.com/sites/4WTSl4BNjd1q9QFEFibC6h/lOvLnhItj8S8-1vyjH_s33Jn-WmUXPmiJ5Diajl0Q38.CMutaHYl.mjs) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 24.81 \| percent \| reported \| Higher is better \| \| `cost` \| 0.64 \| USD \| per_task \| Lower is better \| ### Configuration benchmarkVersion 1.0.6 costFootnote false Fallback policy Not reported Reasoning effort high Model configuration GPT-5.6 Sol (High) thinkingEnabled true ### Reported statistics rank 28 ### Source [Original source](https://framerusercontent.com/sites/4WTSl4BNjd1q9QFEFibC6h/lOvLnhItj8S8-1vyjH_s33Jn-WmUXPmiJ5Diajl0Q38.CMutaHYl.mjs) Source zapier Original model label GPT-5.6 Sol (High) Observed 2026-10-21T16:34:56.783Z Evidence SHA-256 `43978e38f018789fa59c11de5328abe9e5905bfa9a5a4d601fa3aa4d9c153b0d` Source locator `/rows/27` |  |  |  |  |  |  |  |
| [FrontierCode 1.1 main](https://benchize.com/benchmarks/frontiercode%3Av1_1%3Amain.md) | 45.06% | — | 49 / 125 | $3.48 | — | [frontiercode](https://cognition.com/data/frontiercode-leaderboard/data.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.4506 \| score_fraction \| blocking_criteria_adjusted \| Higher is better \| \| `correct` \| 0.5028 \| score_fraction \| raw_rubric \| Higher is better \| \| `cost` \| 3.4801 \| USD \| per_rollout \| Lower is better \| ### Configuration harness codex Reasoning effort high sourceVersion v1_1 subset main ### Reported statistics flaggedRate 0.0013 sampleSize 100 ### Source [Original source](https://cognition.com/data/frontiercode-leaderboard/data.json) Source frontiercode Original model label GPT-5.6 Sol Observed 2026-10-22T05:40:03.220Z Evidence SHA-256 `ff0040778b7bdf69c705ad7474f771fb5e53cfaf5cf8573b3a4614153543d75f` Source locator `/v1_1/data/GPT-5.6%20Sol/high/main` |  |  |  |  |  |  |  |
| [FrontierCode 1.1 extended](https://benchize.com/benchmarks/frontiercode%3Av1_1%3Aextended.md) | 58.74% | — | 42 / 125 | $2.93 | — | [frontiercode](https://cognition.com/data/frontiercode-leaderboard/data.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.5874 \| score_fraction \| blocking_criteria_adjusted \| Higher is better \| \| `correct` \| 0.6475 \| score_fraction \| raw_rubric \| Higher is better \| \| `cost` \| 2.9349 \| USD \| per_rollout \| Lower is better \| ### Configuration harness codex Reasoning effort high sourceVersion v1_1 subset extended ### Reported statistics flaggedRate 0.0008 sampleSize 150 ### Source [Original source](https://cognition.com/data/frontiercode-leaderboard/data.json) Source frontiercode Original model label GPT-5.6 Sol Observed 2026-10-22T05:40:03.220Z Evidence SHA-256 `ff0040778b7bdf69c705ad7474f771fb5e53cfaf5cf8573b3a4614153543d75f` Source locator `/v1_1/data/GPT-5.6%20Sol/high/extended` |  |  |  |  |  |  |  |
| [Short Story Writing — Pairwise Comparison](https://benchize.com/benchmarks/lechmazur-short-story%3Apairwise.md) | 2.28 | 95% CI 2.2–2.37 | 11 / 50 | — | — | [lechmazur short story · 8ba548d1cffefa5c472d3832e05f64e119a88fa4](https://api.github.com/repos/lechmazur/writing/contents/data/writing_gemini_argon_20261013/ratings.csv?ref=8ba548d1cffefa5c472d3832e05f64e119a88fa4) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `thurstone_rating` \| 2.280340865497532 \| index \| pooled_observed_panel \| Higher is better \| \| `win_probability` \| 0.8078821627327935 \| score_fraction \| comparison_pool \| Higher is better \| ### Configuration benchmarkScope data/writing_gemini_argon_20261013 Reasoning effort high thinkingEnabled true ### Reported statistics Uncertainty 95% confidence interval: 2.2–2.37 bootstrapSamples 300 confidenceInterval95 ["2.2032537397212977","2.3714404005146013"] sourceRank 11 ### Source [Original source](https://api.github.com/repos/lechmazur/writing/contents/data/writing_gemini_argon_20261013/ratings.csv?ref=8ba548d1cffefa5c472d3832e05f64e119a88fa4) Source lechmazur short story Original model label GPT-5.6 Sol (high) Source version 8ba548d1cffefa5c472d3832e05f64e119a88fa4 Observed 2026-10-22T07:10:06.634Z Evidence SHA-256 `c36baebed9f302ff7ad8fe97907d72e1757a015a39b6a3b23437597cf8e3bff6` Source locator `/rows/10` |  |  |  |  |  |  |  |
| [ARC-AGI-3](https://benchize.com/benchmarks/arc-prize%3Av3_Semi_Private.md) | 2.15% | — | 22 / 65 | 15,176.07usd | — | [arc prize · v3](https://arcprize.org/media/data/leaderboard/v3.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.0215 \| score_fraction \| v3_Semi_Private \| Higher is better \| \| `total_cost` \| 15176.07 \| usd \| v3_Semi_Private \| Lower is better \| ### Configuration evaluationSplit v3_Semi_Private harness standard modelGroup openai-gpt-5-6-sol modelType CoT Reasoning effort high sourceModelVersion openai-gpt-5-6-sol-high thinkingEnabled true ### Source [Original source](https://arcprize.org/media/data/leaderboard/v3.json) Source arc prize Original model label GPT-5.6 Sol (High) Source version v3 Observed 2026-10-22T05:20:04.578Z Evidence SHA-256 `3ce335487296bb2dcf4ba9546c5a2a02b1907db5b08887cd9ff4429fed824916` Source locator `/evaluations/9` |  |  |  |  |  |  |  |

---
Cite as: GPT-5.6 SolHigh — Benchize, https://benchize.com/models/gpt-5-6-sol-high (retrieved 2026-10-22)