GPT-5.5 Instant: benchmark scores, price and ranking
GPT-5.5 Instant from OpenAI ranks #417 of 743 LLMs on the LLMs Tiger aggregate benchmark score (47.6), based on 11 benchmark results captured up to 2026-10-13.
- Organisation
- OpenAI
- Type
- Frontier model
- Open weights
- No
- Released
- 2026-05-05 (source: epoch)
- Aggregate rank
- #417 of 743 (score 47.6)
Relative to other models, GPT-5.5 Instant is strongest on Epoch ECI (#40 of 204) and weakest on LMArena Document Elo (#18 of 18).
Across the 11 benchmarks where at least ten models are scored, GPT-5.5 Instant is in the top 10% on 0 and in the top half on 4.
GPT-5.5 Instant benchmark results
| Benchmark | Score | Rank | Source | Captured |
|---|---|---|---|---|
| Epoch ECI | 143 | #40 of 204 | Epoch AI Benchmarking Hub | 2026-10-13 |
| GPQA Diamond | 82.5% | #95 of 275 | Epoch AI Benchmarking Hub | 2026-10-13 |
| SciCode | 48.6% | #41 of 106 | Epoch AI Benchmarking Hub | 2026-10-13 |
| OTIS Mock AIME | 68.1% | #82 of 189 | Epoch AI Benchmarking Hub | 2026-10-13 |
| Chess Puzzles | 12.0% | #62 of 122 | Epoch AI Benchmarking Hub | 2026-10-13 |
| LMArena Vision Elo | 1,276 | #13 of 22 | LMArena | 2026-10-05 |
| FrontierMath T1-3 | 26.3% | #52 of 68 | Epoch AI Benchmarking Hub | 2026-10-13 |
| CritPt | 0.0% | #97 of 115 | Epoch AI Benchmarking Hub | 2026-10-13 |
| LMArena Text Elo | 1,473 | #24 of 28 | LMArena | 2026-10-05 |
| FrontierMath T4 | 2.4% | #49 of 50 | Epoch AI Benchmarking Hub | 2026-10-13 |
| LMArena Document Elo | 1,403 | #18 of 18 | LMArena | 2026-10-13 |
About GPT-5.5 Instant
GPT-5.5 Instant is a frontier model from OpenAI. It was released on 2026-05-05, according to Epoch AI. No API price is listed for it yet. We hold 11 benchmark results for it across 3 areas, and none is in the top tenth of its board.
Where GPT-5.5 Instant stands
On our aggregate score, GPT-5.5 Instant is #417 of 743 ranked models, around the middle of the table. Its score is 47.6; the scale is centred on 50, so it sits 2.4 points below the typical model. That beats 44% of the ranked field. Among the 88 ranked OpenAI models it is #51. The next one up is GPT-5.1 (Thinking, Medium) at 47.8. The next one down is GPT-5.1 (Thinking, Low) at 47.5.
GPT-5.5 Instant, benchmark by benchmark
Epoch ECI puts GPT-5.5 Instant at 143, #40 of 204. That beats 80% of the models tested, but 14 points short of Qwen 3.8 Max (156). The results either side are Claude Opus 4 (143) and qwen3.5-35b-a3b (143). It covers Epoch Capabilities Index: Epoch's own aggregate of ~40 benchmarks. The board median is 127, so GPT-5.5 Instant is 15 points above it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
On GPQA Diamond, GPT-5.5 Instant reaches 82.5%. It ranks #95 of 275, ahead of 65% of the field, and 13.3 points behind GPT-6 Astra (max) at 95.8%. The results either side are Qwen 3.6 Flash (2026-04-16) (83.3%) and Claude Sonnet 4.5 (59k thinking) (82.3%). It covers expert-level science questions. The board median is 71.7%, so GPT-5.5 Instant is 10.8 points above it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
GPT-5.5 Instant manages 48.6% on SciCode, good for #41 of 106. Claude Opus 5.5 (max) leads at 66.9%, 18.3 points further up, and 61% of models sit below. The results either side are Qwen3.7 Max (48.8%) and Kimi K2.7 Code (47.5%). It covers scientific research code. The board median is 44.3%, so GPT-5.5 Instant is 4.3 points above it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
OTIS Mock AIME puts GPT-5.5 Instant at 68.1%, #82 of 189. That beats 57% of the models tested, but 31.9 points short of Claude Fable 5.1 (max) (100.0%). The results either side are claude-sonnet-4-20250514_59K (68.9%) and seed-oss-36b-instruct (67.5%). It covers competition maths (AIME 2024-25 style). The board median is 57.8%, so GPT-5.5 Instant is 10.3 points above it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
GPT-5.5 Instant lands below the middle on Chess Puzzles: 12.0%, #62 of 122, with 50% of the field scoring higher. GPT-6 Astra (max) leads at 72.0%; the closest result above is seed-oss-36b-instruct at 13.0%. It covers chess tactics puzzles. The board median is 12.5%, so GPT-5.5 Instant is 0.5 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
GPT-5.5 Instant lands below the middle on LMArena Vision Elo: 1,276, #13 of 22, with 55% of the field scoring higher. Gemini 3.7 Flash (high) leads at 1,296; the closest result above is gpt-5.2-chat-latest-20260210 at 1,278. It covers crowd-voted image understanding. The board median is 1,279, so GPT-5.5 Instant is 3 points below it. Source: LMArena, captured 2026-10-05.
CritPt is a weak spot. GPT-5.5 Instant scores 0.0%, #97 of 115, behind 83% of the models measured. The leader, GPT-5.6 Sol (max), reaches 32.3%. It covers unpublished research-level physics problems. The board median is 2.9%, so GPT-5.5 Instant is 2.9 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
LMArena Text Elo is a weak spot. GPT-5.5 Instant scores 1,473, #24 of 28, behind 82% of the models measured. The leader, gemini-4-argon-high, reaches 1,525. It covers head-to-head chat preference (crowd votes). The board median is 1,478, so GPT-5.5 Instant is 4 points below it. Source: LMArena, captured 2026-10-05.
FrontierMath T4 is a weak spot. GPT-5.5 Instant scores 2.4%, #49 of 50, behind 96% of the models measured. The leader, GPT-6.1 Sol (max), reaches 100.0%. It covers research-level maths, tier 4. The board median is 30.5%, so GPT-5.5 Instant is 28.0 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
LMArena Document Elo is a weak spot. GPT-5.5 Instant scores 1,403, #18 of 18, behind 94% of the models measured. The leader, Claude Fable 5.1 (max), reaches 1,513. It covers crowd-voted questions about documents. The board median is 1,440, so GPT-5.5 Instant is 36 points below it. Source: LMArena, captured 2026-10-13.
The full table above also lists the other 1 result, including boards with fewer than ten models, where a rank says little.
Strengths and weaknesses
Reasoning, maths and science: uneven, ahead of 33% of the field on average across 5 benchmarks. Its best board here is GPQA Diamond (#95 of 275) and its weakest is FrontierMath T4 (#49 of 50). General knowledge and chat: uneven, ahead of 37% of the field on average across 5 benchmarks. Its best board here is Epoch ECI (#40 of 204) and its weakest is LMArena Document Elo (#18 of 18).
Release history
The OpenAI model released before it was gpt-5.5-xhigh (codex-harness) on 2026-04-23, which scores 47.1. The next one was GPT-5.6 Luna (max) on 2026-07-09, at 55.1.
Reading these numbers
The 11 scores on this page come from 2 sources: Epoch AI Benchmarking Hub (8), LMArena (3). No official leaderboard supplied any of them, so treat them as third-party measurements.
Models ranked nearby
- #414 ollama/codestral (47.6)
- #415 Gemini 2.5 Flash (Preview) (Thinking 24K) (47.6)
- #416 Qwen2-VL-72B-Instruct (47.6)
- #418 Qwen2.5-VL-72B-Instruct (47.6)
- #419 GPT-5.1 (Thinking, Low) (47.5)
- #420 grok-4-1 (47.5)
More from OpenAI
- GPT-6 Astra (max) (#2, 64.0)
- GPT-6.1 Sol (max) (#5, 60.6)
- GPT-5.6 Sol (max) (#6, 60.1)
- GPT-6 Sol (max) (#7, 60.0)
- GPT-5.5 (xhigh) (#11, 58.0)
- GPT-5.6 Terra (max) (#12, 57.8)
Compare it on the live leaderboard → · How the aggregate score works