grok-4.3 (high): benchmark scores, price and ranking
grok-4.3 (high) from xAI ranks #315 of 743 LLMs on the LLMs Tiger aggregate benchmark score (48.9), based on 12 benchmark results captured up to 2026-10-13.
- Organisation
- xAI
- Type
- Frontier model
- Open weights
- No
- Released
- 2026-04-17 (source: epoch)
- Cheapest API price
- $1.25 in / $2.50 out per million tokens (via azure_ai, observed 2026-10-13T19:47Z)
- Aggregate rank
- #315 of 743 (score 48.9)
Relative to other models, grok-4.3 (high) is strongest on GPQA Diamond (#42 of 275) and weakest on GDP.pdf (#24 of 25).
Across the 12 benchmarks where at least ten models are scored, grok-4.3 (high) is in the top 10% on 0 and in the top half on 7.
Its cheapest listed input price, $1.25 per million tokens, is lower than that of 26% of the 427 models with a listed price.
grok-4.3 (high) benchmark results
| Benchmark | Score | Rank | Source | Captured |
|---|---|---|---|---|
| GPQA Diamond | 88.8% | #42 of 275 | Epoch AI Benchmarking Hub | 2026-10-13 |
| OTIS Mock AIME | 93.3% | #32 of 189 | Epoch AI Benchmarking Hub | 2026-10-13 |
| DTBench | 90.7% | #25 of 146 | Epoch AI Benchmarking Hub | 2026-10-13 |
| Chess Puzzles | 25.0% | #33 of 122 | Epoch AI Benchmarking Hub | 2026-10-13 |
| LMCA | 38.3% | #33 of 108 | Epoch AI Benchmarking Hub | 2026-10-13 |
| CritPt | 8.0% | #43 of 115 | Epoch AI Benchmarking Hub | 2026-10-13 |
| SciCode | 47.3% | #43 of 106 | Epoch AI Benchmarking Hub | 2026-10-13 |
| FrontierMath T1-3 | 42.8% | #43 of 68 | Epoch AI Benchmarking Hub | 2026-10-13 |
| SimpleQA Verified | 33.2% | #46 of 69 | Epoch AI Benchmarking Hub | 2026-10-13 |
| ProofBench | 11.0% | #35 of 46 | Epoch AI Benchmarking Hub | 2026-10-13 |
| FrontierMath T4 | 14.6% | #40 of 50 | Epoch AI Benchmarking Hub | 2026-10-13 |
| GDP.pdf | 8.0% | #24 of 25 | Epoch AI Benchmarking Hub | 2026-10-13 |
About grok-4.3 (high)
grok-4.3 (high) is a frontier model from xAI. It was released on 2026-04-17, according to Epoch AI. The cheapest API listing we track charges $1.25 per million input tokens and $2.50 per million output tokens, through azure_ai. We hold 12 benchmark results for it across 4 areas, and none is in the top tenth of its board.
Where grok-4.3 (high) stands
On our aggregate score, grok-4.3 (high) is #315 of 743 ranked models, around the middle of the table. Its score is 48.9; the scale is centred on 50, so it sits 1.1 points below the typical model. That beats 58% of the ranked field. Among the 26 ranked xAI models it is #17. The next one up is grok-4.20-beta1 at 49.0. The next one down is grok-4.20-beta-0309-reasoning at 48.7.
grok-4.3 (high), benchmark by benchmark
GPQA Diamond puts grok-4.3 (high) at 88.8%, #42 of 275. That beats 85% of the models tested, but 6.9 points short of GPT-6 Astra (max) (95.8%). The results either side are Ornith-1.5-35B-A3B (89.2%) and Inkling Small (xhigh) (88.5%). It covers expert-level science questions. The board median is 71.7%, so grok-4.3 (high) is 17.1 points above it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
On OTIS Mock AIME, grok-4.3 (high) reaches 93.3%. It ranks #32 of 189, ahead of 83% of the field, and 6.7 points behind Claude Fable 5.1 (max) at 100.0%. The results either side are GLM-5.1 (93.3%) and Qwen 3.6 Plus (2026-04-02) (93.3%). It covers competition maths (AIME 2024-25 style). The board median is 57.8%, so grok-4.3 (high) is 35.6 points above it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
grok-4.3 (high) manages 90.7% on DTBench, good for #25 of 146. Claude Opus 5.5 (max) leads at 98.9%, 8.3 points further up, and 83% of models sit below. The results either side are GPT-5 (high) (90.7%) and GPT-5.1 (high) (90.1%). It covers dynamic tool-use benchmark. The board median is 68.8%, so grok-4.3 (high) is 21.9 points above it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
Chess Puzzles puts grok-4.3 (high) at 25.0%, #33 of 122. That beats 73% of the models tested, but 47.0 points short of GPT-6 Astra (max) (72.0%). The results either side are Qwen3.6 35B-A3B (26.0%) and GPT-5.4 mini (xhigh) (24.0%). It covers chess tactics puzzles. The board median is 12.5%, so grok-4.3 (high) is 12.5 points above it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
On LMCA, grok-4.3 (high) reaches 38.3%. It ranks #33 of 108, ahead of 69% of the field, and 29.9 points behind Claude Opus 5.5 (max) at 68.2%. The results either side are grok-4-20 (38.7%) and Qwen3.5 397B-A17B (37.9%). It covers language-model capability assessment. The board median is 29.2%, so grok-4.3 (high) is 9.1 points above it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
grok-4.3 (high) manages 8.0% on CritPt, good for #43 of 115. GPT-5.6 Sol (max) leads at 32.3%, 24.3 points further up, and 63% of models sit below. The results either side are Qwen3.7 Plus (9.1%) and Kimi K2.6 (8.0%). It covers unpublished research-level physics problems. The board median is 2.9%, so grok-4.3 (high) is 5.1 points above it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
grok-4.3 (high) lands below the middle on SimpleQA Verified: 33.2%, #46 of 69, with 65% of the field scoring higher. gemini-4-argon-high leads at 76.0%; the closest result above is DeepSeek V4 Flash 0731 (max) at 33.6%. It covers short factual questions. The board median is 41.0%, so grok-4.3 (high) is 7.8 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
grok-4.3 (high) lands below the middle on ProofBench: 11.0%, #35 of 46, with 74% of the field scoring higher. Claude Fable 5.1 (max) leads at 100.0%; the closest result above is GPT-5 nano (high) at 12.0%. It covers writing mathematical proofs. The board median is 21.0%, so grok-4.3 (high) is 10.0 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
grok-4.3 (high) lands below the middle on FrontierMath T4: 14.6%, #40 of 50, with 78% of the field scoring higher. GPT-6.1 Sol (max) leads at 100.0%; the closest result above is Inkling Small (xhigh) at 17.1%. It covers research-level maths, tier 4. The board median is 30.5%, so grok-4.3 (high) is 15.9 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
GDP.pdf is a weak spot. grok-4.3 (high) scores 8.0%, #24 of 25, behind 92% of the models measured. The leader, GPT-6 Astra (max), reaches 34.2%. It covers economically valuable document tasks. The board median is 22.8%, so grok-4.3 (high) is 14.8 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
The full table above also lists the other 2 results, including boards with fewer than ten models, where a rank says little.
Strengths and weaknesses
Reasoning, maths and science: solid, ahead of 52% of the field on average across 6 benchmarks. Its best board here is GPQA Diamond (#42 of 275) and its weakest is FrontierMath T4 (#40 of 50). Agents and tool use: uneven, ahead of 43% of the field on average across 2 benchmarks. Its best board here is DTBench (#25 of 146) and its weakest is GDP.pdf (#24 of 25). General knowledge and chat: solid, ahead of 59% of the field on average across 3 benchmarks. Its best board here is Chess Puzzles (#33 of 122) and its weakest is SimpleQA Verified (#46 of 69).
Price and value
The median input price across the 427 priced models is $0.500 per million tokens, so grok-4.3 (high) 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), Qwen3.7 Flash ($0.030, 50.5). Similar scores cost more on Codex Mini (Latest) ($1.50) and Magistral Medium ($1.50).
Release history
The xAI model released before it was Grok 4.20 (Reasoning) on 2026-02-17, which scores 51.2. The next one was grok-build-0.1 on 2026-05-29, at 45.4.
Reading these numbers
The 12 scores on this page come from 1 source: Epoch AI Benchmarking Hub (12). No official leaderboard supplied any of them, so treat them as third-party measurements. The leaderboard also lists 2 other reasoning-effort settings of this model, which redirect here. This page shows the highest.
grok-4.3 (high) is also listed at 2 other reasoning-effort settings; this page shows the highest-effort row, which is the one the leaderboard keeps by default.
Models ranked nearby
- #312 deepseek-v4-pro-high-20260813 (48.9)
- #313 qwen-plus-2025-04-28 (48.9)
- #314 Inkling (xhigh) (48.9)
- #316 claude-opus-4-5-20251101-high-32k (48.9)
- #317 DeepSeek V4.1 Flash (high) (48.9)
- #318 Gemini 3.6 Flash (High) (48.9)
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