Model evidence profile

GPT-5.6 Sol

OpenAI · Proprietary · Reasoning

currentsupported
Overall public score
82.20
Source rank
#4
Evidence coverage
7 benchmarks · 2 sources

Strongest published evidencePublic overall score 82.2 at source rank #4.

Validate before choosingValidate the selected route price, context limits, and evidence freshness before choosing.

Revision benchmark_3b14dc55ef5307cfe91356d3ea348101 · Published Aug 30, 2026 · Checked Aug 30, 2026 · stale

Relative field position

Capability radar

Percentiles use eligible source ranks. Missing axes remain unavailable and never become zero.

Capability ranking percentile radarAgenticCodingKnowledgeMathMultimodal groundedOverallReasoning
Agentic percentile
93.5 percentileRank #10 of 140
Coding percentile
98.6 percentileRank #3 of 145
Knowledge percentile
94.4 percentileRank #4 of 55
Math percentile
Math: Unavailable
Multimodal grounded percentile
88.2 percentileRank #5 of 35
Overall percentile
Overall: Unavailable
Reasoning percentile
Reasoning: Unavailable

Published measurements

Category scores

Scores retain their source units; percentile and rank appear only for eligible fields.

Agenticsupported
68.9
Rank
#10 of 140
Percentile
93.5%
Benchmarks
7
Codingsupported
79.0
Rank
#3 of 145
Percentile
98.6%
Benchmarks
7
Knowledgesupported
86.0
Rank
#4 of 55
Percentile
94.4%
Benchmarks
7
Mathsupported
97.0
Rank
Not ranked
Percentile
Unavailable
Benchmarks
7
Overallsupported
82.2
Rank
#4
Percentile
Unavailable
Benchmarks
7
Reasoningsupported
85.2
Rank
Not ranked
Percentile
Unavailable
Benchmarks
7

Route-specific facts

Pricing and specifications

Conflicting routes remain separate and attributable.

openaibenchlm:gpt-5-6-sol
primary
Input / 1M
$5.00
Cached input / 1M
$0.50
Output / 1M
$30.00
Context
1,050,000
View price source
Context window
1,050,000
Maximum output
Unavailable
Input modalities
Unavailable
Output modalities
Unavailable
Release date
2026-07-09
Self hosting
Not verified

Auditable evidence

Benchmark ledger

Display values, source ranks, and provenance remain visible without implying unsupported aggregate weight.

agentic

ScoreRankWeightLast UpdatedSource
68.88#10Not publishedAug 29, 2026BenchLM

coding

ScoreRankWeightLast UpdatedSource
79.01#3Not publishedAug 29, 2026BenchLM

knowledge

ScoreRankWeightLast UpdatedSource
86.00#4Not publishedAug 29, 2026BenchLM

math

ScoreRankWeightLast UpdatedSource
97.00Not rankedNot publishedAug 29, 2026BenchLM

multimodalGrounded

ScoreRankWeightLast UpdatedSource
82.70#5Not publishedAug 29, 2026BenchLM

reasoning

ScoreRankWeightLast UpdatedSource
85.20Not rankedNot publishedAug 29, 2026BenchLM

overall

ScoreRankWeightLast UpdatedSource
82.20#4Not publishedAug 29, 2026BenchLM

Related evidence

Compare this model