# GPT-5.5Medium

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

OpenAI

Canonical URL: https://benchize.com/models/gpt-5-5-medium
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 |  |
| --- | --- | --- | --- | --- | --- | --- | --- |
| [FrontierCode 1 main](https://benchize.com/benchmarks/frontiercode%3Av1%3Amain.md) | 22.42% | — | 15 / 39 | $3.29 | — | [frontiercode](https://cognition.com/data/frontiercode-leaderboard/data.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.2242 \| score_fraction \| blocking_criteria_adjusted \| Higher is better \| \| `correct` \| 0.248 \| score_fraction \| raw_rubric \| Higher is better \| \| `cost` \| 3.2931 \| USD \| per_rollout \| Lower is better \| ### Configuration harness codex Reasoning effort medium sourceVersion v1 subset main ### Reported statistics flaggedRate Not reported sampleSize 100 ### Source [Original source](https://cognition.com/data/frontiercode-leaderboard/data.json) Source frontiercode Original model label GPT-5.5 Observed 2026-10-22T05:40:03.220Z Evidence SHA-256 `ff0040778b7bdf69c705ad7474f771fb5e53cfaf5cf8573b3a4614153543d75f` Source locator `/v1/data/GPT-5.5/medium/main` |  |  |  |  |  |  |  |
| [NC Bench](https://benchize.com/benchmarks/nc-bench%3Aoverall.md) | 93.72% | — | 21 / 144 | — | — | [nc bench](https://www.nc-bench.com/models) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 93.72 \| percent \| reported \| Higher is better \| \| `tooling` \| 100 \| percent \| category \| Higher is better \| \| `creative_writing` \| 90.26 \| percent \| category \| Higher is better \| \| `language` \| 99.69 \| percent \| category \| Higher is better \| \| `utility` \| 96.6 \| percent \| category \| Higher is better \| \| `reasoning` \| 92.87 \| percent \| category \| Higher is better \| \| `text_editing` \| 98.79 \| percent \| category \| Higher is better \| \| `rule_following` \| 79.4 \| percent \| category \| Higher is better \| \| `hallucination` \| 92.12 \| percent \| category \| Higher is better \| ### Configuration Reasoning effort medium Model configuration GPT-5.5 (Reasoning, Medium) thinkingEnabled true ### Source [Original source](https://www.nc-bench.com/models) Source nc bench Original model label GPT-5.5 (Reasoning, Medium) Observed 2026-10-22T06:10:03.426Z Evidence SHA-256 `ec261022458543624b08a136d01f5a2f0666cd52ffb49c64d6ca983e8543d1b5` Source locator `/rows/27` |  |  |  |  |  |  |  |
| [DeepSWE](https://benchize.com/benchmarks/deepswe%3Av1.1.md) | 53.98% | Range 51.43–56.54% | 41 / 70 | $2.75 | 1,289s | [deepswe](https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `pass_at_1` \| 0.5398230088495575 \| score_fraction \| scored_rollout_attempts \| Higher is better \| \| `pass_at_4` \| 0.7787610619469026 \| score_fraction \| tasks_with_one_passing_rollout \| Higher is better \| \| `cost_per_attempt` \| 2.749342734513274 \| USD \| scored_attempt \| Lower is better \| \| `duration` \| 1288.995063800885 \| seconds \| scored_attempt \| Lower is better \| ### Configuration harness mini-swe-agent Reasoning effort medium sourceConfiguration mini_swe_agent_gpt_5_5_medium ### Reported statistics Uncertainty Reported interval: 51.43–56.54% interval [0.5142921338966476,0.5653538838024673] intervalMethod 95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R)) runCount 4 sampleSize 452 taskCount 113 ### Source [Original source](https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json) Source deepswe Original model label gpt-5-5 Observed 2026-10-22T03:50:05.889Z Evidence SHA-256 `a7c15d66288fd249c020b9931c017b92d1a3b90e480b3ff34974b752bd030019` Source locator `/rows/40` |  |  |  |  |  |  |  |
| [FrontierCode 1 extended](https://benchize.com/benchmarks/frontiercode%3Av1%3Aextended.md) | 42.29% | — | 15 / 39 | $2.77 | — | [frontiercode](https://cognition.com/data/frontiercode-leaderboard/data.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.4229 \| score_fraction \| blocking_criteria_adjusted \| Higher is better \| \| `correct` \| 0.464 \| score_fraction \| raw_rubric \| Higher is better \| \| `cost` \| 2.77 \| USD \| per_rollout \| Lower is better \| ### Configuration harness codex Reasoning effort medium sourceVersion v1 subset extended ### Reported statistics flaggedRate Not reported sampleSize 150 ### Source [Original source](https://cognition.com/data/frontiercode-leaderboard/data.json) Source frontiercode Original model label GPT-5.5 Observed 2026-10-22T05:40:03.220Z Evidence SHA-256 `ff0040778b7bdf69c705ad7474f771fb5e53cfaf5cf8573b3a4614153543d75f` Source locator `/v1/data/GPT-5.5/medium/extended` |  |  |  |  |  |  |  |
| [AutomationBench](https://benchize.com/benchmarks/zapier%3Aautomationbench.md) | 8.98% | — | 73 / 113 | $0.75 | — | [zapier](https://framerusercontent.com/sites/4WTSl4BNjd1q9QFEFibC6h/lOvLnhItj8S8-1vyjH_s33Jn-WmUXPmiJ5Diajl0Q38.CMutaHYl.mjs) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 8.98 \| percent \| reported \| Higher is better \| \| `cost` \| 0.75 \| USD \| per_task \| Lower is better \| ### Configuration benchmarkVersion 1.0.6 costFootnote false Fallback policy Not reported Reasoning effort medium Model configuration GPT-5.5 (Medium) thinkingEnabled true ### Reported statistics rank 83 ### Source [Original source](https://framerusercontent.com/sites/4WTSl4BNjd1q9QFEFibC6h/lOvLnhItj8S8-1vyjH_s33Jn-WmUXPmiJ5Diajl0Q38.CMutaHYl.mjs) Source zapier Original model label GPT-5.5 (Medium) Observed 2026-10-21T16:34:56.783Z Evidence SHA-256 `43978e38f018789fa59c11de5328abe9e5905bfa9a5a4d601fa3aa4d9c153b0d` Source locator `/rows/82` |  |  |  |  |  |  |  |
| [ARC-AGI-1](https://benchize.com/benchmarks/arc-prize%3Av1_Semi_Private.md) | 92.17% | — | 56 / 245 | 0.39usd per task | — | [arc prize · v1](https://arcprize.org/media/data/leaderboard/v1.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.9217 \| score_fraction \| v1_Semi_Private \| Higher is better \| \| `cost_per_task` \| 0.39 \| usd_per_task \| v1_Semi_Private \| Lower is better \| ### Configuration evaluationSplit v1_Semi_Private harness Not reported modelGroup gpt-5-5-2026-04-22-thinking modelType CoT Reasoning effort medium sourceModelVersion gpt-5-5-2026-04-22-thinking-medium thinkingEnabled true ### Source [Original source](https://arcprize.org/media/data/leaderboard/v1.json) Source arc prize Original model label GPT-5.5 (Medium) Source version v1 Observed 2026-10-22T05:20:04.066Z Evidence SHA-256 `2bf68d22dafba37047d07ad833ebc0e8199c9aa2f9eeaed50c75c1b704462836` Source locator `/evaluations/147` |  |  |  |  |  |  |  |
| [FrontierCode 1.1 extended](https://benchize.com/benchmarks/frontiercode%3Av1_1%3Aextended.md) | 51.37% | — | 81 / 125 | $1.98 | — | [frontiercode](https://cognition.com/data/frontiercode-leaderboard/data.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.5137 \| score_fraction \| blocking_criteria_adjusted \| Higher is better \| \| `correct` \| 0.5679 \| score_fraction \| raw_rubric \| Higher is better \| \| `cost` \| 1.9847 \| USD \| per_rollout \| Lower is better \| ### Configuration harness codex Reasoning effort medium sourceVersion v1_1 subset extended ### Reported statistics flaggedRate 0 sampleSize 150 ### Source [Original source](https://cognition.com/data/frontiercode-leaderboard/data.json) Source frontiercode Original model label GPT-5.5 Observed 2026-10-22T05:40:03.220Z Evidence SHA-256 `ff0040778b7bdf69c705ad7474f771fb5e53cfaf5cf8573b3a4614153543d75f` Source locator `/v1_1/data/GPT-5.5/medium/extended` |  |  |  |  |  |  |  |
| [ARC-AGI-2](https://benchize.com/benchmarks/arc-prize%3Av2_Semi_Private.md) | 70.42% | — | 54 / 243 | 0.86usd per task | — | [arc prize · v2](https://arcprize.org/media/data/leaderboard/v2.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.7042 \| score_fraction \| v2_Semi_Private \| Higher is better \| \| `cost_per_task` \| 0.86 \| usd_per_task \| v2_Semi_Private \| Lower is better \| ### Configuration evaluationSplit v2_Semi_Private harness Not reported modelGroup gpt-5-5-2026-04-22-thinking modelType CoT Reasoning effort medium sourceModelVersion gpt-5-5-2026-04-22-thinking-medium thinkingEnabled true ### Source [Original source](https://arcprize.org/media/data/leaderboard/v2.json) Source arc prize Original model label GPT-5.5 (Medium) Source version v2 Observed 2026-10-22T05:20:04.306Z Evidence SHA-256 `4351eb696e78113b0459e9bb5f0258318b905efef34f473dcea51ce641b0d94d` Source locator `/evaluations/148` |  |  |  |  |  |  |  |
| [ToneBench Scriptwriting](https://benchize.com/benchmarks/tonebench%3Ascripts.md) | 1,530 | Range 1,491.8–1,583 | 75 / 126 | — | — | [tonebench](https://benchmark.towardsai.com/data/leaderboard.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1530 \| rating \| reported \| Higher is better \| \| `overall` \| 75.8 \| percent \| reported \| Higher is better \| \| `anti_slop_numbers` \| 68.04 \| source_score \| rubric \| Higher is better \| \| `continuity_emotion` \| 77.74 \| source_score \| rubric \| Higher is better \| \| `cue_quality` \| 78.68 \| source_score \| rubric \| Higher is better \| \| `hook_strength` \| 80.94 \| source_score \| rubric \| Higher is better \| \| `length_adherence` \| 35.86 \| source_score \| rubric \| Higher is better \| \| `slop` \| 80.92 \| source_score \| rubric \| Higher is better \| \| `slop_score` \| 93.81 \| source_score \| rubric \| Higher is better \| \| `substance_accuracy` \| 84.28 \| source_score \| rubric \| Higher is better \| \| `tone_voice` \| 78.92 \| source_score \| rubric \| Higher is better \| \| `writing_quality` \| 75.42 \| source_score \| rubric \| Higher is better \| \| `youtube_best_practices` \| 77.62 \| source_score \| rubric \| Higher is better \| ### Configuration provider codex Reasoning effort unknown scoreScope 10_task_current sourceConfiguration gpt-5-5 thinkingEnabled true ### Reported statistics Uncertainty Reported interval: 1,491.8–1,583 interval [1491.8,1583] rank 76 runCount 5 ### Source [Original source](https://benchmark.towardsai.com/data/leaderboard.json) Source tonebench Original model label GPT-5.5 (medium) Evaluated 2026-10-11 Observed 2026-10-22T04:40:14.102Z Evidence SHA-256 `4264338337f418d3ded7ace250cad64fe12cacbd4b79a312bfaf0ae9268a01c3` Source locator `/rows/75` |  |  |  |  |  |  |  |
| [FrontierCode 1.1 main](https://benchize.com/benchmarks/frontiercode%3Av1_1%3Amain.md) | 36.6% | — | 84 / 125 | $2.35 | — | [frontiercode](https://cognition.com/data/frontiercode-leaderboard/data.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.366 \| score_fraction \| blocking_criteria_adjusted \| Higher is better \| \| `correct` \| 0.4108 \| score_fraction \| raw_rubric \| Higher is better \| \| `cost` \| 2.3513 \| USD \| per_rollout \| Lower is better \| ### Configuration harness codex Reasoning effort medium sourceVersion v1_1 subset main ### Reported statistics flaggedRate 0 sampleSize 100 ### Source [Original source](https://cognition.com/data/frontiercode-leaderboard/data.json) Source frontiercode Original model label GPT-5.5 Observed 2026-10-22T05:40:03.220Z Evidence SHA-256 `ff0040778b7bdf69c705ad7474f771fb5e53cfaf5cf8573b3a4614153543d75f` Source locator `/v1_1/data/GPT-5.5/medium/main` |  |  |  |  |  |  |  |

---
Cite as: GPT-5.5Medium — Benchize, https://benchize.com/models/gpt-5-5-medium (retrieved 2026-10-22)