whatmodel.sh / GPT-6.1 Sol

GPT-6.1 Sol

+ contribute

GPT-6.1 Sol is a closed-weights language model from OpenAI, released September 2026. Licence: proprietary.

Catalogue identity notes

Official API model gpt-6.1-sol, distinct from GPT-6 Sol. Arena evaluation uses max reasoning.

Model information sources

Release date ↗

85.3±0.8#3 of 719 LLMsfrom 19 benchmark results across 6 sources

$ how it compares

The LLMs ranked either side of GPT-6.1 Sol, out of 828 with a score, then more from OpenAI.

#	model	score	where	released
1	GPT-6 Astra OpenAI	87±1	api $20.00/M	2026-09
2	Claude Opus 5.5 Anthropic	87±1	api $8.00/M	2026-09
3	GPT-6.1 Sol OpenAI	85±1	api $4.00/M	2026-09
4	Claude Fable 5.1 Anthropic	85±1	api $20.00/M	2026-09
5	Claude Sonnet 5.5 Anthropic	84±1	api $4.00/M	2026-09
	more from OpenAI
7	GPT-6 Sol OpenAI	83±1	api $4.00/M	2026-09
8	GPT-5.5 Pro OpenAI	82±1	api $67.50/M	2026-04
10	GPT-5.6 Sol OpenAI	82±1	api $8.00/M	2026-07

see all LLMs · find the ones that fit your machine

$ what it's good at

agent tasks▁▁▃▆█▆▅▅▅▄▃▃ #4 of 300 * · 18% of its score · 2 tests

Beats GPT-6 Astra here, though they rank higher overall. Trails Claude Sonnet 5.5, Claude Fable 5.1 here, though they rank lower overall.

test	result	vs the others in its run	difficulty	counts	why
Arena Agent (October 2026 aggregate IPS)	0.1123 IPS ✎	▁▁▁▄▂▃▇█▂▂▃▃ beats 45/49	avg -0.312 IPS	▇▇▇▇ 10%	sharp
Terminal-Bench 4.0	58.2% ✎	█▅▅▅▅·▅▃▃▅▅▅ beats 18/20	very hard · avg 0.4%	▇▇▇ 7.7%	sharp · at its level

coding▁▁▁▃▆██▇▆▄▃▃ #4 of 458 * · 11% of its score · 2 tests

Trails Claude Sonnet 5.5 here, though they rank lower overall.

test	result	vs the others in its run	difficulty	counts	why
Arena WebDev (Code Arena)	1757.8 ✎	▁▂▄▃▅█▄▇▆▄▁▃ beats 116/119	avg 981	▇▇▇▇ 9.0%	sharp
Luau Leetcode fully solved (Torpedo Software)	87.0% ✎	▁▁▁▁·▁▂▃▅▃█▇ beats 47/49	hard · avg 18%	▇ 1.8%	typical

chat & writing▁▁▁▃▅▄▅█▆▆▇▃ #17 of 393 * · 5.0% of its score · 1 test

Beats GPT-6 Astra here, though they rank higher overall. Trails Gemini 3.6 Flash, Claude Opus 4.6, Muse Spark 1.1 here, though they rank lower overall.

test	result	vs the others in its run	difficulty	counts	why
LMArena (text)	1483.2 ✎	▁▁▁▂▃▃▃▆▆▇█▃ beats 362/379	avg 1268	▇▇ 5.0%	blunt

math▁▂▃▅▆▅▄█▄▁▁▃ #2 of 398 · 18% of its score · 3 tests

Beats Claude Opus 5.5 here, though they rank higher overall.

test	result	vs the others in its run	difficulty	counts	why
FrontierMath tier 4 v2	100.0% ✎	▁▂▁▂█▅▂▂▁▁▁▃ beats 63/63	very hard · avg 0.1%	▇▇▇▇ 11%	sharp
FrontierMath tiers 1–3 v2	93.7% ✎	▂··▁▁▃▄▄█▅▃▃ beats 81/82	very hard · avg 1.2%	▇▇▇ 6.9%	sharp · maxed out
OTIS mock AIME 2024–2025	100.0% ✎	▃▃▄▃▃▃▇▇█▃▂▅ beats 187/193	very hard · avg 8.5%	▇ 0.1%	sharp · maxed out · noisy

vision & documents▁▁▃▂▁▃▄▂▆▇█▄ #13 of 147 * · 3.5% of its score · 1 test

Trails Claude Opus 4.7, Muse Spark 1.2, Qwen3.8-Flash-Next here, though they rank lower overall.

test	result	vs the others in its run	difficulty	counts	why
Arena vision (style controlled)	1290.6 ✎	▁▁▂▂▂▂▄▅▅▆██ beats 138/145	avg 1068	▇ 3.5%	blunt

other tests10 not in a task · 45% of its score

test	result	vs the others in its run	difficulty	counts	why
EBR-bench (Epoch)	54.3% ✎	▄▂·▆█▂▆▄▆▆·▄ beats 20/23	very hard · avg 0.3%	▇▇▇▇▇▇ 15%	sharp · at its level
Mystery Game Puzzles (Epoch)	80.0% ✎	█··▂▃▇▄█▂▃▁▃ beats 73/74	very hard · avg 9.4%	▇▇▇▇ 9.3%	sharp · at its level · noisy
Furniture Assembly (Epoch)	80.0% ✎	█▆▆▆▆▂▅▂▂▂·▅ beats 28/30	very hard · avg 1.2%	▇▇▇ 8.4%	sharp · at its level
Chess Puzzles (Epoch)	61.0% ✎	█▁▁▁▁▂▁▄▂▂▁▃ beats 132/135	very hard · avg 5.9%	▇▇ 4.9%	sharp · at its level · noisy
SimpleQA Verified	73.9% ✎	▁▁▃▂▃▃▆▆█▃▂▅ beats 77/78	very hard · avg 8.0%	▇ 1.7%	at its level
Icelandic LLM Leaderboard average (Miðeind, Sept 2026 suite)	68.2% ✎	▁▁▃▂▂▄▁▃▄▄▄█ beats 34/38	very hard · avg 14%	▇ 1.6%	at its level
HealthBench Hard lab	33.4% ✎	▂··▂····▂▄·█ beats 5/8	very hard · avg 9.7%	▇ 1.3%	blunt · at its level
GPQA Diamond	95.4% ✎	▁▁▁▁▂▄▆▄▅▇█▅ beats 205/208	hard · avg 40%	▇ 1.2%	sharp · maxed out

2 more tests

test	result	vs the others in its run	difficulty	counts	why
HealthBench lab	56.7% ✎	▃·▃·····█▃▃▅ beats 5/8	hard · avg 24%	▇ 1.1%	blunt · at its level
RobloxQA v2.0 multiple choice (Torpedo Software)	98.6% ✎	▁▁▃▁█▄▃▃▆▂▂▃ beats 48/49	easy · avg 78%	▇ 0.7%	maxed out

$ where to run it

Through an API

api · $4.00/M · $2 in / $10 out per 1M tokens · 1.1M context · developers.openai.com ↗ · price sourceObserved 2026-10-06. USD per million tokens, Standard, prompts up to 272K input tokens; longer prompts 2x input and 1.5x output. Fast/regional premiums excluded.

$ how the score was worked out · Epoch AI — internal evaluatio… 58%, LMArena leaderboard dataset 28%, Terminal-Bench 4.0 official l… 8% and 3 more

Each result implies a score on its own, after adjusting for how hard its test is and who ran it. The score is their weighted average, with a small pull toward the middle for thinly tested models. Each test's weight is its counts column above; here it's added up by who ran the tests. How it works

source	results	share of the score	licence
Epoch AI — internal evaluations	9	▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 58%	CC BY 4.0
LMArena leaderboard dataset	4	▇▇▇▇▇▇▇▇ 28%	CC BY 4.0
Terminal-Bench 4.0 official leaderboard submissions	1	▇▇ 8%	Apache-2.0
Roblox LLM Leaderboard (Torpedo Software): RobloxQA v2.0 and Luau Leetcode	2	▇ 2%	MIT
OpenAI vendor-reported benchmark scores for its own models (openai.com announcement posts and Deployment Safety Hub system cards) · lab-reported	2	▇ 2%	Factual vendor-reported score (not licensed content)
Miðeind Icelandic LLM Leaderboard	1	▇ 2%	CC BY 4.0
prior · pull toward the middle		▇ 0%
weighted average		= 85.3