AI BENCHY
Advertise here
#101

GPT-5.6 Sol

OpenAI Release: 2026-07-09 Tested on: 2026-07-09 21:15 openai/gpt-5.6-sol::none
~2T total (~150B active)MoEClosedEstimated
(high) (medium) (low) (none)

Summary

GPT-5.6 Sol scores 6.3 on AI BENCHY and ranks #101. It has 10.0 reliability, a 57.1% pass rate, $0.225 total cost, and 1.66s average response time.

What makes GPT-5.6 Sol unique: It is notably fast compared with similar models.

Model facts

Researched on 2026-08-12

Estimated
Parameters
~2T total (~150B active)
Architecture
MoE
Availability
Closed
License
-

Best estimate from public evidence; the vendor did not disclose every value. Vendor does not disclose the architecture or count.

Parameter source Availability source

Score

6.3

Consistency

9.0

Reliability

10.0

Total Cost (Current Price)

$0.225

Total Output Tokens

1,776

Total Input Tokens

34,218

Input Price

$5.000 / 1M

Output Price

$30.000 / 1M

Tests Correct

Wrong Tests: 11

Attempt pass rate: 57.1%

Flaky tests

3

Flaky tests had mixed outcomes across runs (at least one pass and one fail).

Response Time (avg)

1.66s

Response Time (max): 3.93s

Response Time (total): 34.81s

Wrong answer: 10 Did not follow instructions: 1

Hamster playing table tennis

Prompt: Create a detailed SVG illustration of a hamster playing table tennis.

#101 GPT-5.6 Sol

none
Cost
$0.116
Time
78.7s
Tokens
3,944 tok

Run history

Tested on Score Reliability Tests Correct Total Cost Compare
2026-08-14 02:21 Re-test 7.0 10.0 $0.524 Compare
2026-07-16 22:37 New test added 6.9 10.0 $0.524 Compare
2026-07-09 21:15 Initial run 6.3 10.0 $0.225 Current run

Run comparison

RunBenchmark coverageScoreConsistencyReliabilityTests CorrectFlaky testsTotal Output TokensTotal Input TokensTotal CostResponse Time (avg)
2026-07-09 21:15 · Initial run63/63 attempts6.39.010.010/2131,77634,218$0.2251.66s
2026-07-16 22:37 · New test added66/66 attempts6.99.010.011/2234,35778,593$0.5242.16s
Difference—-0.60.00.0-10-2581-44375-$0.300-507ms

Benchmark coverage differs: 63/63 attempts (Target: 3 repeats per test) versus 66/66 attempts (Target: 3 repeats per test). Totals and repeat-sensitive metrics are not directly comparable.

These two runs used different benchmark suites, so the deltas reflect both model changes and suite changes.

Price History

Historical pricing data for this model from OpenRouter.

Date Input Price Output Price
2026-07-09 21:18 $5.000 / 1M $30.000 / 1M

Charts

Choose the first model, then click a second model to open a side-by-side page.

Total Output Tokens

Score vs Total Output Tokens

Quick Compare

GPT-5.6 SolnonevsGrok 4.3mediumGPT-5.6 SolnonevsDeepSeek V3.2mediumGPT-5.6 SolnonevsSolar Pro 4highGPT-5.6 SolnonevsGLM 5.1mediumGPT-5.6 SolnonevsStep 3.7 FlashlowGPT-5.6 SolnonevsGPT-5.5noneGPT-5.6 SolnonevsMuse Glimmer 30BlowGPT-5.6 SolnonevsMercury 2mediumGPT-5.6 SolnonevsQwen3.5-122B-A10BmediumGPT-5.6 SolnonevsGrok 4.20medium

Category Breakdown

Category Score Consistency Tests Correct
Anti-AI Tricks 8.3 10.0
Coding 5.5 10.0
Combined 3.0 10.0
Data parsing and extraction 10.0 10.0
Domain specific 3.6 7.2
General Intelligence 6.5 3.4
Instructions following 8.5 6.8
Puzzle Solving 7.7 10.0
Tool Calling 10.0 10.0
Trivia 3.0 10.0

Compared models