grok-build-0.1: benchmark scores, price and ranking
grok-build-0.1 from xAI ranks #590 of 743 LLMs on the LLMs Tiger aggregate benchmark score (45.4), based on 10 benchmark results captured up to 2026-10-13.
- Organisation
- xAI
- Type
- Frontier model
- Open weights
- No
- Released
- 2026-05-29 (source: epoch)
- Cheapest API price
- $1.00 in / $2.00 out per million tokens (via aihubmix, observed 2026-10-13T19:47Z)
- Aggregate rank
- #590 of 743 (score 45.4)
Relative to other models, grok-build-0.1 is strongest on SciCode (#34 of 106) and weakest on LiveBench Coding (#17 of 17).
Across the 9 benchmarks where at least ten models are scored, grok-build-0.1 is in the top 10% on 0 and in the top half on 2.
Its cheapest listed input price, $1.00 per million tokens, is lower than that of 34% of the 427 models with a listed price.
grok-build-0.1 benchmark results
| Benchmark | Score | Rank | Source | Captured |
|---|---|---|---|---|
| GBA-Eval | 2.4% | #1 of 7 | Epoch AI Benchmarking Hub | 2026-10-13 |
| SciCode | 50.2% | #34 of 106 | Epoch AI Benchmarking Hub | 2026-10-13 |
| CritPt | 9.1% | #41 of 115 | Epoch AI Benchmarking Hub | 2026-10-13 |
| LiveBench Agentic Coding | 45.8% | #9 of 17 | LiveBench 2026_06_25 official CSV | 2026-10-13 |
| LiveBench IF | 65.2% | #9 of 17 | LiveBench 2026_06_25 official CSV | 2026-10-13 |
| LiveBench Data Analysis | 70.8% | #10 of 17 | LiveBench 2026_06_25 official CSV | 2026-10-13 |
| LiveBench Reasoning | 76.4% | #13 of 17 | LiveBench 2026_06_25 official CSV | 2026-10-13 |
| LiveBench Language | 72.5% | #14 of 17 | LiveBench 2026_06_25 official CSV | 2026-10-13 |
| LiveBench Mathematics | 78.4% | #16 of 17 | LiveBench 2026_06_25 official CSV | 2026-10-13 |
| LiveBench Coding | 65.4% | #17 of 17 | LiveBench 2026_06_25 official CSV | 2026-10-13 |
About grok-build-0.1
grok-build-0.1 is a frontier model from xAI. It was released on 2026-05-29, according to Epoch AI. The cheapest API listing we track charges $1.00 per million input tokens and $2.00 per million output tokens, through aihubmix. We hold 10 benchmark results for it across 4 areas, and none is in the top tenth of its board.
Where grok-build-0.1 stands
On our aggregate score, grok-build-0.1 is #590 of 743 ranked models, in the lower half. Its score is 45.4; the scale is centred on 50, so it sits 4.6 points below the typical model. That beats 21% of the ranked field. Among the 26 ranked xAI models it is #24. The next one up is grok-3 at 46.5. The next one down is grok-code-fast-1 at 44.3.
grok-build-0.1, benchmark by benchmark
SciCode puts grok-build-0.1 at 50.2%, #34 of 106. That beats 68% of the models tested, but 16.7 points short of Claude Opus 5.5 (max) (66.9%). The results either side are DeepSeek V4 Pro 0813 (max) (51.0%) and mimo-v2.5-pro (50.2%). It covers scientific research code. The board median is 44.3%, so grok-build-0.1 is 5.9 points above it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
On CritPt, grok-build-0.1 reaches 9.1%. It ranks #41 of 115, ahead of 64% of the field, and 23.1 points behind GPT-5.6 Sol (max) at 32.3%. The results either side are GPT-5.4 nano (xhigh) (9.3%) and Qwen3.7 Plus (9.1%). It covers unpublished research-level physics problems. The board median is 2.9%, so grok-build-0.1 is 6.3 points above it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
grok-build-0.1 lands below the middle on LiveBench Agentic Coding: 45.8%, #9 of 17, with 47% of the field scoring higher. claude-opus-4-8-xhigh-effort leads at 56.1%; the closest result above is GPT-5.4 nano (xhigh) at 46.8%. It covers LiveBench release 2026_06_25. The median score on this board is also 45.8%. Source: LiveBench 2026_06_25 official CSV, captured 2026-10-13.
grok-build-0.1 lands below the middle on LiveBench IF: 65.2%, #9 of 17, with 47% of the field scoring higher. gemini-3.1-pro-preview-high leads at 79.1%; the closest result above is GPT-5.2 Codex at 66.4%. It covers LiveBench release 2026_06_25. The median score on this board is also 65.2%. Source: LiveBench 2026_06_25 official CSV, captured 2026-10-13.
grok-build-0.1 lands below the middle on LiveBench Data Analysis: 70.8%, #10 of 17, with 53% of the field scoring higher. GPT-5.5 (xhigh) leads at 81.6%; the closest result above is Qwen3.7 Max at 71.8%. It covers LiveBench release 2026_06_25. The board median is 71.8%, so grok-build-0.1 is 1.0 points below it. Source: LiveBench 2026_06_25 official CSV, captured 2026-10-13.
grok-build-0.1 lands below the middle on LiveBench Reasoning: 76.4%, #13 of 17, with 71% of the field scoring higher. claude-opus-4-8-xhigh-effort leads at 89.7%; the closest result above is GPT-5.2 Codex at 77.7%. It covers LiveBench release 2026_06_25. The board median is 81.1%, so grok-build-0.1 is 4.7 points below it. Source: LiveBench 2026_06_25 official CSV, captured 2026-10-13.
LiveBench Language is a weak spot. grok-build-0.1 scores 72.5%, #14 of 17, behind 76% of the models measured. The leader, GPT-5.5 (xhigh), reaches 87.4%. It covers LiveBench release 2026_06_25. The board median is 77.9%, so grok-build-0.1 is 5.4 points below it. Source: LiveBench 2026_06_25 official CSV, captured 2026-10-13.
LiveBench Mathematics is a weak spot. grok-build-0.1 scores 78.4%, #16 of 17, behind 88% of the models measured. The leader, GPT-5.5 (xhigh), reaches 95.9%. It covers LiveBench release 2026_06_25. The board median is 88.2%, so grok-build-0.1 is 9.8 points below it. Source: LiveBench 2026_06_25 official CSV, captured 2026-10-13.
LiveBench Coding is a weak spot. grok-build-0.1 scores 65.4%, #17 of 17, behind 94% of the models measured. The leader, GPT-5.2 Codex, reaches 83.6%. It covers LiveBench release 2026_06_25. The board median is 76.5%, so grok-build-0.1 is 11.1 points below it. Source: LiveBench 2026_06_25 official CSV, captured 2026-10-13.
The full table above also lists the other 1 result, including boards with fewer than ten models, where a rank says little.
Strengths and weaknesses
Software engineering: uneven, ahead of 38% of the field on average across 3 benchmarks. Its best board here is SciCode (#34 of 106) and its weakest is LiveBench Coding (#17 of 17). Reasoning, maths and science: uneven, ahead of 31% of the field on average across 3 benchmarks. Its best board here is CritPt (#41 of 115) and its weakest is LiveBench Mathematics (#16 of 17). General knowledge and chat: uneven, ahead of 35% of the field on average across 3 benchmarks. Its best board here is LiveBench IF (#9 of 17) and its weakest is LiveBench Language (#14 of 17).
Price and value
The median input price across the 427 priced models is $0.500 per million tokens, so grok-build-0.1 costs more than the typical listing. Models that score within 1.5 points or better and cost less: Qwen2.5-Coder-7B-Instruct ($0.010, 49.5), DeepSeek V4.1 Flash (high) ($0.010, 48.9), Qwen2.5-Coder-3B-Instruct ($0.010, 46.5). Similar scores cost more on mimo-v2-pro ($1.10) and o3-mini-2025-01-31 (low) ($1.10).
Release history
The xAI model released before it was grok-4.3 (high) on 2026-04-17, which scores 48.9. The next one was Grok 4.5 (high) on 2026-07-08, at 52.0.
Reading these numbers
The 10 scores on this page come from 2 sources: LiveBench 2026_06_25 official CSV (7), Epoch AI Benchmarking Hub (3). 7 of them come from an official leaderboard and 3 from datasets or third-party runs.
Models ranked nearby
- #587 internlm2-math-plus-20b (45.4)
- #588 LLaDA-8B-Instruct (45.4)
- #589 Llama-3-Smaug-8B (45.4)
- #591 mistral-medium-2505 (45.4)
- #592 Devstral Small 2 (45.4)
- #593 Command R+ (45.4)
More from xAI
- Grok 4.6 (xhigh) (#34, 53.6)
- grok-4-0709 (#38, 53.2)
- Grok 4 (#39, 53.2)
- Grok 4.7 (xhigh) (#41, 53.1)
- Grok 4.5 (high) (#85, 52.0)
- Grok 4.20 (Reasoning) (#136, 51.2)
Compare it on the live leaderboard → · How the aggregate score works