whatmodel.sh / GPT-3.5 Turbo (0125)

GPT-3.5 Turbo (0125)

+ contribute

GPT-3.5 Turbo (0125) is a closed-weights language model from OpenAI, released January 2024. Licence: proprietary.

Catalogue identity notes

Comparison model from the Epoch AI internal-evaluation CSVs (Epoch release date 2024-01-25). Dated API snapshot gpt-3.5-turbo-0125 (default snapshot of 'gpt-3.5-turbo'). OpenAI's deprecations page schedules its shutdown for October 23, 2026 (announced 2026-04-22).

46.4±0.5#411 of 719 LLMsfrom 35 benchmark results across 17 sources

$ how it compares

The LLMs ranked either side of GPT-3.5 Turbo (0125), out of 828 with a score, then more from OpenAI.

#	model	score	where	RAM	released
487	EuroLLM 9B Instruct UTTER (EuroLLM)	47±3	local	~6.9GB	2024-11
488	Granite 4.0 H Micro 3B IBM	47±1	local	~3.4GB	2025-09
489	GPT-3.5 Turbo (0125) OpenAI	46±1	api $0.75/M		2024-01
490	Mistral Large (2402) Mistral	46±1	comparison only		2024-02
491	Jamba 1.5 Mini AI21 Labs	46±1	local	~34GB	2024-08
	more from OpenAI
1	GPT-6 Astra OpenAI	87±1	api $20.00/M		2026-09
3	GPT-6.1 Sol OpenAI	85±1	api $4.00/M		2026-09
7	GPT-6 Sol OpenAI	83±1	api $4.00/M		2026-09

see all LLMs · find the ones that fit your machine

$ what it's good at

agent tasks▁▁▃▆█▆▅▅▅▄▃▁ #243 of 300 * · 0.5% of its score · 1 test

Beats DeepSeek R1 0528 Qwen3 8B, Sky-T1 32B Preview, Magistral Small 1.0 (2506) here, though they rank higher overall. Trails Granite 4.0 1B, SmolLM3 3B, Phi-3.5-mini-instruct here, though they rank lower overall.

test	result	vs the others in its run	difficulty	counts	why
BFCL v3	52.5% ✎	▁▁▁▁▁▃▅█▅▄▁▁ beats 47/114	medium · avg 52%	▇ 0.5%	blunt · at its level

coding▁▁▁▃▆██▇▆▄▃▁ #269 of 458 · 22% of its score · 3 tests

Beats Qwen3-VL 32B Instruct, Solar Open 100B (102B-A12B), GLM-4.7-Flash here, though they rank higher overall. Trails DeepSeek LLM 67B Chat, Mistral NeMo Instruct (2407), QwQ-32B-Preview here, though they rank lower overall.

test	result	vs the others in its run	difficulty	counts	why
HumanEval	76.8% ✎	▁█▄▅▇█·▄▇▅▄▄ beats 38/42	easy · avg 78%	▇▇▇▇ 10%	sharp · at its level
CRUXEval (ZeroEval, 800 problems)	54.8% ✎	▁▂▆▃▆█▆▃▂·▁▁ beats 15/47	medium · avg 61%	▇▇▇ 6.8%	sharp · at its level
Aider code editing (133 Exercism Python exercises, two attempts)	50.4% ✎	▁·▁▂▄▁▆▄█▆▂▂ beats 15/62	medium · avg 54%	▇▇ 4.4%	at its level

chat & writing▁▁▁▃▅▄▅█▆▆▇▃ #291 of 393 · 13% of its score · 5 tests

Beats Ministral 3 14B Reasoning 2512, Gemma 4 E4B, OpenThinker3 7B here, though they rank higher overall. Trails Flan-T5 XXL, LFM2 700M, EXAONE 3.5 2.4B Instruct here, though they rank lower overall.

test	result	vs the others in its run	difficulty	counts	why
Arena-Hard (v0.1, GPT-4-1106 judge)	23.3% ✎	▂▁▁▅█▅▄▃▃▅▃▁ beats 20/60	medium · avg 52%	▇▇ 6.0%	sharp · at its level
Polyrating rating (bias-aware re-fit of Chatbot Arena votes, mid-2024)	1147.0 ✎	▂▁▂▁▃▇█▆▇▄▂▂ beats 64/95	avg 1201	▇ 2.3%	blunt
LMArena (text)	1225.5 ✎	▁▁▁▂▃▃▃▆▆▇█▃ beats 80/379	avg 1268	▇ 2.3%	blunt
AlpacaEval 2 length-controlled	38.7% ✎	▃▃·▁▁█▇▅·▁·▁ beats 13/22	medium · avg 42%	▇ 1.5%	at its level
IFEval prompt-level loose	66.9% ✎	▁▃▁▃▃▄▁▁█▃▃▁ beats 6/22	easy · avg 80%	▇ 0.5%	typical

math▁▂▃▅▆▅▄█▄▁▁▁ #342 of 398 · 13% of its score · 7 tests

Trails Qwen3 0.6B, Gemma 7B (base), Qwen2.5 1.5B Instruct here, though they rank lower overall.

test	result	vs the others in its run	difficulty	counts	why
GSM8K (ZeroEval, zero-shot)	80.4% ✎	▁▄·▁▄█▅▅▅███ beats 12/43	very easy · avg 89%	▇▇ 3.8%	sharp
MATH level 5	11.6% ✎	▂▂▅▆▄█▆▃▅▂▃▄ beats 8/92	hard · avg 32%	▇ 3.6%	sharp
MATH Level 5 (ZeroEval, 721 problems)	13.7% ✎	▁▁▃▆█▂▇▇▄··▂ beats 2/38	hard · avg 34%	▇ 2.6%	sharp
GSM8K	74.3% ✎	▂▃··▃▃▅█▆▃▂▃ beats 5/22	very easy · avg 88%	▇ 1.5%	sharp
MATH (subset unspecified)	41.2% ✎	▃▃█▂▂▆·····▁ beats 10/22	medium · avg 61%	▇ 0.9%	at its level
OTIS mock AIME 2024–2025	2.2% ✎	▃▃▄▃▃▃▇▇█▃▂▅ beats 17/193	very hard · avg 8.5%	▇ 0.4%	sharp · too hard for it · noisy
FrontierMath tiers 1–3 v2	0.0% ✎	▃··▁▁▃▄▄█▅▃▃ beats 1/82	very hard · avg 1.2%	▇ 0.3%	sharp · too hard for it

other tests19 not in a task · 52% of its score

test	result	vs the others in its run	difficulty	counts	why
MMLU-Redux (ZeroEval, 2,778 questions)	68.4% ✎	▁·▁▁▄▄▄▅█▄▂▁ beats 13/53	easy · avg 77%	▇▇▇▇▇ 11%	at its level
LiveBench 2024-07-26	34.5% ✎	▁▁▁▂▂▃▂█▆▃▅▃ beats 37/61	medium · avg 41%	▇▇▇▇ 9.1%	at its level
EvoEval (overall)	53.1% ✎	▂▂▃▄▄█▁▄▅▃▁▃ beats 37/42	medium · avg 55%	▇▇▇ 7.3%	at its level
BIG-Bench Hard	66.6% ✎	▁▄·▁▁·▅█·▄▄▁ beats 9/22	easy · avg 75%	▇ 3.4%	sharp · at its level
MMLU	70.2% ✎	▁▂·▁·▁▁█·▃▃▅ beats 10/22	easy · avg 77%	▇ 3.2%	at its level
BigCodeBench (Instruct)	38.2% ✎	▃▂·▆▆██▆▅▃▃▃ beats 22/33	medium · avg 41%	▇ 2.8%	at its level
BigCodeBench (Complete)	50.6% ✎	▂▁▁▄▂▅▇█▆▃▂▂ beats 51/58	medium · avg 50%	▇ 2.8%	at its level
WildBench v2 WB-Score (task macro)	30.0160 WB-Score ✎	▁·▁▁·▃█▄▇▆▅▆ beats 14/52	avg 45.199 WB-Score	▇ 2.6%	sharp

11 more tests

test	result	vs the others in its run	difficulty	counts	why
ZebraLogic (ZeroEval, 1,000 puzzles)	10.1% ✎	▁▁▃▆██▁▁·▁▁▁ beats 10/57	hard · avg 18%	▇ 2.4%	sharp
GPQA Diamond	27.2% ✎	▁▁▃▁▂▄▆▄▅▇█▅ beats 10/208	hard · avg 40%	▇ 2.0%	sharp
HindiGen-v1 3C3H score (Inception, Claude 3.5 Sonnet judge)	49.1% ✎	▁▁▁▁·▂·█▆█▇▁ beats 6/31	medium · avg 48%	▇ 1.2%	at its level
BRIDGE clinical text, zero-shot average (87 tasks)	35.3% ✎	▁▁▁▁▁▂▂▃▄▆█▃ beats 47/97	hard · avg 32%	▇ 1.1%	blunt · at its level
Open Persian LLM Leaderboard v2 average (21 tasks)	50.7% ✎	▂▄▂▃█▄▃▆▃▅▂▂ beats 35/81	medium · avg 58%	▇ 1.0%	blunt · at its level
PopQA	45.0% ✎	▁▁▁▃▃▃▁█▁▃·▄ beats 19/21	hard · avg 32%	▇ 0.6%	blunt · at its level
Open PT-LLM Leaderboard average (9 Portuguese tasks)	72.2% ✎	▃▁▁▁▁▁▁▁▂█▅▁ beats 193/276	medium · avg 73%	▇ 0.5%	at its level · noisy
TruthfulQA MC2	62.9% ✎	▃▃▂·▃▃·▅█▂▅▂ beats 10/21	medium · avg 63%	▇ 0.5%	blunt · at its level
Icelandic LLM Leaderboard average (Miðeind, Sept 2026 suite)	12.9% ✎	▁▁▃▂▂▄▁▃▄▄▄█ beats 2/38	very hard · avg 14%	▇ 0.3%	typical
Chess Puzzles (Epoch)	0.0% ✎	█▁▁▁▁▂▁▄▂▂▁▁ beats 14/135	very hard · avg 5.9%	▇ 0.1%	sharp · too hard for it · noisy
Mystery Game Puzzles (Epoch)	3.0% ✎	█··▂▃▇▄█▂▃▁▁ beats 3/74	very hard · avg 9.4%	▇ 0.0%	sharp · too hard for it · noisy

$ where to run it

Through an API

api · $0.75/M · $0.5 in / $1.5 out per 1M tokens · 16k context · developers.openai.com ↗ · price sourceUSD per 1M tokens, OpenAI API standard processing, model page 'gpt-3.5-turbo' whose default snapshot is gpt-3.5-turbo-0125: input $0.5, output $1.5; cached-input, Batch and other tiers excluded. Currency: USD. OpenAI official model page, observed 2026-09-28.

$ how the score was worked out · WildEval ZeroEval published r… 27%, Top Leaderboard Ranking = Top… 18%, 2 OLMo 2 Furious (Team OLMo,… 12% and 14 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
WildEval ZeroEval published results	5	▇▇▇▇▇▇▇▇ 27%	Apache-2.0
Top Leaderboard Ranking = Top Coding Proficiency, Always? EvoEval: Evolving Coding Benchmarks via LLM — authors' own runs	2	▇▇▇▇▇ 18%	CC BY 4.0
2 OLMo 2 Furious (Team OLMo, Ai2) — authors' own evaluations of OLMo 2 Instruct and peer instruct models	8	▇▇▇▇ 12%	CC BY 4.0
LiveBench model judgments (HF livebench/model_judgment, 2024-10-22 revision) with the LiveBench question datasets	1	▇▇▇ 9%	Apache-2.0 (stated in the LiveBench datasheet)
Epoch AI — internal evaluations	6	▇▇ 6%	CC BY 4.0
Arena-Hard-Auto v0.1 leaderboard (repository README, pre-v2)	1	▇▇ 6%	Apache-2.0
BigCodeBench paper (Zhuo et al., ICLR 2025), arXiv 2406.15877v4	2	▇▇ 6%	CC BY 4.0
Aider code editing benchmark runs (old edit leaderboard)	1	▇ 4%	Apache-2.0
WildBench v2 leaderboard data (Ai2)	1	▇ 3%	Apache-2.0
Polyrating: A Cost-Effective and Bias-Aware Rating System for LLM Evaluation (arXiv:2409.00696v3)	1	▇ 2%	CC-BY-4.0
LMArena leaderboard dataset	1	▇ 2%	CC BY 4.0
Inception Arabic/Hindi leaderboards (AraGen-v3, HindiGen-v1, Arabic IFEval)	1	▇ 1%	Apache-2.0
BRIDGE Medical Leaderboard (Harvard Medical School / Brigham and Women's YLab)	1	▇ 1%	MIT
Open Persian LLM Leaderboard v2 (Part DP AI and AUT NLP Lab)	1	▇ 1%	Apache-2.0
Open Portuguese LLM Leaderboard (archived)	1	▇ 1%	Apache-2.0
Berkeley Function Calling Leaderboard result archive	1	▇ 1%	Apache-2.0
Miðeind Icelandic LLM Leaderboard	1	▇ 0%	CC BY 4.0
prior · pull toward the middle		▇ 0%
weighted average		= 46.4