Grok 4.6

+ contribute

Grok 4.6 is a closed-weights language model from SpaceXAI (xAI), released August 2026.

76.5±0.7#30 of 719 LLMsfrom 18 benchmark results across 5 sources

$ how it compares

The LLMs ranked either side of Grok 4.6, out of 828 with a score, then more from SpaceXAI (xAI).

#	model	score	where	RAM	released
28	GPT-6 Luna OpenAI	77±1	api $0.20/M		2026-09
29	GPT-5.6 Luna OpenAI	77±1	api $0.45/M		2026-07
30	Grok 4.6 SpaceXAI (xAI)	77±1	api $3.00/M		2026-08
31	DeepSeek V4 Pro (0813) DeepSeek	76±1	api $1.63/M +local	~1010GB	2026-08
32	Gemini 3.7 Flash Google	76±1	api $1.50/M		2026-08
	more from SpaceXAI (xAI)
42	Grok 4.5 SpaceXAI (xAI)	75±1	api $3.00/M		2026-07
47	Grok 4.7 SpaceXAI (xAI)	75±1	api $3.00/M		2026-09
60	Grok 4.20 Multi-Agent (0309) SpaceXAI (xAI)	73±2	api $1.56/M		2026-03

see all LLMs · find the ones that fit your machine

$ what it's good at

agent tasks▁▁▃▆█▆▅▅▅▄▃▁ #30 of 300 · 14% of its score · 3 tests

Beats GPT-5.4, GPT-6 Luna, GPT-5.6 Luna here, though they rank higher overall. Trails GLM-5.3-Flash, Grok 4.7, Qwen3.8 Max (0902) here, though they rank lower overall.

test	result	vs the others in its run	difficulty	counts	why
Arena Agent (October 2026 aggregate IPS)	0.0128 IPS ✎	▁▁▁▄▂▃▇█▂▂▁▃ beats 25/49	avg -0.312 IPS	▇▇▇ 8.3%	sharp
Terminal-Bench 4.0	20.3% ✎	█▅▅▅▅·▅▃▃▅▅▅ beats 7/20	very hard · avg 0.4%	▇▇ 4.6%	sharp
KlinikeBench strict pass@1 (333 interactive clinical encounters, Terminus-2)	21.9% ✎	▁▁·▁▁▁▁▅▃█▅█ beats 20/27	very hard · avg 2.4%	▇ 1.2%	typical

coding▁▁▁▃▆██▇▆▄▃▁ #20 of 458 * · 10% of its score · 2 tests

Beats GPT-5.5, MiMo-V2.6-Pro, GPT-5.6 Terra here, though they rank higher overall. Trails Grok 4.7, Qwen3.8-Flash-Next, Qwen3.8 Max (0902) here, though they rank lower overall.

test	result	vs the others in its run	difficulty	counts	why
Arena WebDev (Code Arena)	1619.5 ✎	▁▂▄▃▅█▄▇▆▄▁▁ beats 99/119	avg 981	▇▇▇ 7.3%	sharp
Luau Leetcode fully solved (Torpedo Software)	83.7% ✎	▁▁▁▁·▁▂▃▅▃█▇ beats 42/49	hard · avg 18%	▇ 2.6%	typical

chat & writing▁▁▁▃▅▄▅█▆▆▇▃ #51 of 393 * · 4.1% of its score · 1 test

Beats MiMo-V2.6-Flash (309B-A15B), GPT-6 Luna, GPT-5.6 Luna here, though they rank higher overall. Trails Claude Sonnet 4.5, Gemini 3.5 Flash-Lite, MiMo-V2.5-Pro (1T-A42B) here, though they rank lower overall.

test	result	vs the others in its run	difficulty	counts	why
LMArena (text)	1453.8 ✎	▁▁▁▂▃▃▃▆▆▇█▃ beats 320/379	avg 1268	▇▇ 4.1%	blunt

math▁▂▃▅▆▅▄█▄▁▁▁ #27 of 398 · 36% of its score · 3 tests

Beats DeepSeek V4.1 Flash, Gemini 3.8 Flash here, though they rank higher overall. Trails Qwen3.7 Max, Qwen3.8 Max (0902), Gemini 3.7 Flash here, though they rank lower overall.

test	result	vs the others in its run	difficulty	counts	why
FrontierMath tier 4 v2	31.7% ✎	▁▂▁▂█▅▂▂▁▁▁▁ beats 38/63	very hard · avg 0.1%	▇▇▇▇▇▇▇ 18%	sharp · at its level
FrontierMath tiers 1–3 v2	66.0% ✎	▂··▁▁▃▄▄█▅▃▃ beats 54/82	very hard · avg 1.2%	▇▇▇▇▇▇▇ 18%	sharp · at its level
OTIS mock AIME 2024–2025	99.2% ✎	▃▃▄▃▃▃▇▇█▃▂▅ beats 181/193	very hard · avg 8.5%	▇ 0.6%	sharp · maxed out · noisy

vision & documents▁▁▃▂▁▃▄▂▆▇█▄ #35 of 147 * · 4.2% of its score · 2 tests

Beats MiMo-V2.6-Pro, MiMo-V2.6-Flash (309B-A15B), GPT-5.6 Luna here, though they rank higher overall. Trails Qwen3.6 Flash, Qwen3.6 Plus, Qwen3.7 Plus here, though they rank lower overall.

test	result	vs the others in its run	difficulty	counts	why
Arena vision (style controlled)	1263.5 ✎	▁▁▂▂▂▂▄▅▅▆██ beats 111/145	avg 1068	▇ 2.8%	blunt
Arena document (style controlled)	1461.1 ✎	▁▁▃▃▄▃▇█▅▇▄▅ beats 18/37	avg 1335	▇ 1.4%	blunt

other tests7 not in a task · 31% of its score

test	result	vs the others in its run	difficulty	counts	why
EBR-bench (Epoch)	30.5% ✎	▄▂·▆█▂▆▄▆▆·▄ beats 14/23	very hard · avg 0.3%	▇▇▇ 8.7%	sharp
Furniture Assembly (Epoch)	40.0% ✎	█▆▆▆▆▂▅▂▂▂·▅ beats 16/30	very hard · avg 1.2%	▇▇▇ 7.2%	sharp · at its level
Mystery Game Puzzles (Epoch)	34.0% ✎	█··▂▃▇▄█▂▃▁▁ beats 55/74	very hard · avg 9.4%	▇▇ 6.1%	sharp · noisy
Chess Puzzles (Epoch)	31.0% ✎	█▁▁▁▁▂▁▄▃▂▁▁ beats 107/135	very hard · avg 5.9%	▇ 3.7%	sharp · at its level · noisy
GPQA Diamond	93.2% ✎	▁▁▁▁▂▄▆▄▅▇█▅ beats 194/208	hard · avg 40%	▇ 2.7%	sharp
SimpleQA Verified	48.9% ✎	▁▁▃▂▃▃▆▆█▃▂▅ beats 52/78	very hard · avg 8.0%	▇ 1.7%	at its level
RobloxQA v2.0 multiple choice (Torpedo Software)	96.8% ✎	▁▁▃▁█▄▃▃▆▂▂▂ beats 39/49	easy · avg 78%	▇ 0.9%	maxed out

$ where to run it

Through an API

api · xAI · $3.00/M · $2 in / $6 out per 1M tokens · 500k context · docs.x.ai ↗ · price sourceStandard base token rate from models.dev. Provider-specific tiers, long-context surcharges, caching and promotions may differ.

$ how the score was worked out · Epoch AI — internal evaluatio… 67%, LMArena leaderboard dataset 24%, Terminal-Bench 4.0 official l… 5% and 2 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	▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 67%	CC BY 4.0
LMArena leaderboard dataset	5	▇▇▇▇▇▇▇ 24%	CC BY 4.0
Terminal-Bench 4.0 official leaderboard submissions	1	▇ 5%	Apache-2.0
Roblox LLM Leaderboard (Torpedo Software): RobloxQA v2.0 and Luau Leetcode	2	▇ 4%	MIT
KlinikeBench: Evaluating Language Models Beyond Diagnostic Accuracy (arXiv:2609.38480v2)	1	▇ 1%	CC BY 4.0
prior · pull toward the middle		▇ 0%
weighted average		= 76.5