Skip to content
Leaderboard / OpenAI

GPT-5.5

OpenAI xHigh, Codex Harness CLOSED Proprietary
Other settings:High · 92Default · 77High, Codex HarnessCodex Harness
Verdict

GPT-5.5 doesn't have enough test coverage for an overall SIscope score yet. Strongest at math, weaker at coding. On the pricey side: costs more than 97% of priced models.

SIscope score
No score yet
60% coverage, needs 70%
Human-vote rank
Not on board
Text arena
Price per 1M tokens, blended
$11
$5 in · $30 out
Context window
1.1M
1,050,000 tokens

Shape

Each spoke is a category, 0 at the centre, 100 at the edge.

CodingAgentsno data yetReasoningMathChatno data yetInstructionsno data yet

Category scores

Percentiles: 90 means better than about 90% of tested models.

Coding60
Agents & toolsNo data yet–
Reasoning & knowledge87
Math89
Chat qualityNo data yet–
Following instructionsNo data yet–

What goes into each category · Compare with DeepSeek V4.1 Flash

Coding votes over time

WebDev arena, recent updates.

150515131520Oct 16: 1512.7 (rank #54)Oct 18: 1512.6 (rank #56)Oct 19: 1512.6 (rank #58)Oct 22: 1512.6 (rank #58)Oct 23: 1512.5 (rank #59)Oct 27: 1512.1 (rank #60)Oct 28: 1512.1 (rank #61)Oct 16Oct 28

Independent test runs

Run by Epoch AI on the same harness for every model. Bars show the share of questions answered correctly.

SimpleQA Verified63%
Short factual questions; rewards not making things up
Better than 87% of 100 tested models. Run Aug 27, 2026.
FrontierMath Tiers 1-385%
Very hard, unpublished research-style maths problems
Better than 89% of 122 tested models. Run Jun 11, 2026.

Human-vote arenas

People compare two anonymous answers and pick the better one. Scores work like chess ratings.

ArenaRankScoreRange (95%)VotesUpdated
Text arena
Everyday chat, blind human votes
Not on this board yet
WebDev arena
Building web apps, blind human votes
#61 of 15215121506–151815,553Oct 28, 2026
Vision arena
Questions about images, blind human votes
Not on this board yet
Agent arena
Real multi-step agent sessions
Not on this board yet

Source: Arena (formerly LMArena) leaderboard dataset, CC BY 4.0. Fetched Nov 4, 2026.

Price

Input
$5
per 1M tokens
Output
$30
per 1M tokens
Blended
$11
3 in : 1 out, per 1M
Context window
1.1M
max tokens per request
Speed
Coming soon
our own tests

List price from the OpenRouter models API (openai/gpt-5.5), Nov 4, 2026. Providers can charge differently.