GPT-5.6 Sol vs Inkling-Small
Wins 7 of 8 areas
Coding · Agents · Reasoning · Facts · Images and charts · Math · Long documents
Wins 1 of 8 areas
Following instructions
GPT-5.6 Sol is the stronger all-rounder.Inkling-Small is cheaper and better at following instructions.
Scores updated · 39 tests both models report · How we compare
Where each one wins
Tests won in each of the eight areas we test. Each piece is one test, so a longer bar means more evidence; grey means the two scored within a point of each other.
- AgentsCarrying out multi-step tasks on its own50GPT-5.6 Sol5 of 5 tests
- CodingWriting and fixing software40GPT-5.6 Sol4 of 4 tests
- ReasoningHard problems that need careful thinking40GPT-5.6 Sol4 of 4 tests
- Images and chartsUnderstanding pictures, charts and video30GPT-5.6 Sol3 of 3 tests
- MathCompetition and research-level math30GPT-5.6 Sol3 of 3 tests
- FactsGetting facts right instead of making them up21GPT-5.6 Sol2 of 3 tests
- Long documentsFinding answers in very long texts10GPT-5.6 Sol1 of 1 test
- Following instructionsDoing exactly what it is asked01Inkling-Small1 of 1 test
Long documents and following instructions rest on a single test each.
What it costs
Prices per million tokens, roughly 750,000 words. The bars show the cost of a million tokens read plus a million written.
Inkling-Small costs 94% less for the same work.
The biggest differences
The tests each model wins by the widest margin, up to three each. Scores are out of 100.
Where GPT-5.6 Sol pulls ahead
- Extremely hard research-level math problemsFrontierMath Tier 4+65.9points ahead
- Abstract visual puzzles that people can solveARC-AGI-2+52.4points ahead
- Short factual questions, answered correctlySimpleQA Verified+49.1points ahead
Where Inkling-Small pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+29.2points ahead
- Follows unfamiliar, precisely checkable instructionsIFBench+9.5points ahead
Every test, side by side
All 39 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingGPT-5.6 Sol
- Terminal-Bench 2.1GPT-5.6 Sol by 32.98855.1+32.9
- LMArena · WebDevGPT-5.6 Sol by 209 rating points16181409+209 rating
- SWE-bench ProGPT-5.6 Sol by 8.764.655.9+8.7
- SciCodeGPT-5.6 Sol by 7.457.149.7+7.4
AgentsGPT-5.6 Sol
- Terminal-Bench 4.0GPT-5.6 Sol by 38.939.91+38.9
- τ-Bench V3 · BankingGPT-5.6 Sol by 25.544.318.8+25.5
- GDPValGPT-5.6 Sol by 24.455.631.2+24.4
- BrowseCompGPT-5.6 Sol by 1390.477.4+13
- MCP AtlasGPT-5.6 Sol by 483.679.6+4
ReasoningGPT-5.6 Sol
- ARC-AGI-2GPT-5.6 Sol by 52.492.540.1+52.4
- CritPtGPT-5.6 Sol by 2432.38.3+24
- Humanity's Last ExamGPT-5.6 Sol by 16.249.533.3+16.2
- GPQA DiamondGPT-5.6 Sol by 4.694.189.5+4.6
FactsGPT-5.6 Sol
- SimpleQA VerifiedGPT-5.6 Sol by 49.169.720.6+49.1
- AA-Omniscience · Non-hallucinationInkling-Small by 29.27.837+29.2
- AA-Omniscience · AccuracyGPT-5.6 Sol by 26.259.433.2+26.2
Images and chartsGPT-5.6 Sol
- MMMU-ProGPT-5.6 Sol by 9.483.474+9.4
- CharXiv (RQ)GPT-5.6 Sol by 8.485.877.4+8.4
- LMArena · VisionGPT-5.6 Sol by 45 rating points12791234+45 rating
MathGPT-5.6 Sol
- FrontierMath Tier 4GPT-5.6 Sol by 65.98317.1+65.9
- FrontierMath Tiers 1-3 (v2)GPT-5.6 Sol by 42.889.146.3+42.8
- AIME 2026GPT-5.6 Sol by 4.499.995.5+4.4
Following instructionsInkling-Small
- IFBenchInkling-Small by 9.572.782.2+9.5
Other results15 tests, not counted
Tests outside the eight areas. They are not counted above: several are summary scores built from other tests, or the same test under another name.
- GDPval-AA v2GPT-5.6 Sol by 473 rating points17111238+473 rating
- AA-OmniscienceGPT-5.6 Sol by 30.922-8.9+30.9
- AA Agentic IndexGPT-5.6 Sol by 25.550.525+25.5
- Artificial Analysis Coding IndexGPT-5.6 Sol by 24.577.452.9+24.5
- AA IntelligenceGPT-5.6 Sol by 21.34725.7+21.3
- Toolathlon VerifiedGPT-5.6 Sol by 20.574.954.4+20.5
- Artificial AnalysisGPT-5.6 Sol by 195940+19
- τ³-Bench BankingGPT-5.6 Sol by 17.53315.5+17.5
- HLE (with tools)GPT-5.6 Sol by 16.764.547.8+16.7
- ARC-AGI-1GPT-5.6 Sol by 12.596.584+12.5
- SWEBench Pro PublicGPT-5.6 Sol by 8.764.655.9+8.7
- charxiv_rq_with_pythonGPT-5.6 Sol by 6.587.881.3+6.5
- Global-MMLU-LiteGPT-5.6 Sol by 5.191.886.7+5.1
- ToolathlonGPT-5.6 Sol by 3.65854.4+3.6
- StrongREJECTtie98.598.4tie
Questions people ask
Which is better, GPT-5.6 Sol or Inkling-Small?
GPT-5.6 Sol wins seven of the eight areas we test: coding, agents, reasoning, facts, images and charts, math and long documents. Inkling-Small wins following instructions, and costs 94% less.
Which is better for coding?
GPT-5.6 Sol. It wins 4 of the 4 coding tests both models report; Inkling-Small wins none.
Which is cheaper?
GPT-5.6 Sol costs $4.00 per million input tokens and $20.00 per million output tokens; Inkling-Small costs $0.30 and $1.20. That makes Inkling-Small about 94% cheaper for the same work.
How do you compare the two?
We use the 39 benchmark tests both models have published scores on. The verdict counts the 24 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 15 are listed but not counted, because several are summary scores or repeat a test. Each score is the one shown on the model's own page.