SpaceXAIGrok 2
Grok 2 is a SpaceXAI open-weights model, released 12 Dec 2024. Its best configuration ranks #612 of 785 on the BenchLeader Index at 41.9 ±4.5, in the lower half. The ± is the point: 303 other configurations score within that range, so they and this one cannot be told apart on quality alone — price and speed are what separate them. It scores highest in human preference (50) and lowest in coding (32). Last measured 22 Oct 2026.
- Blended price
- –
- Output speed
- –
- First answer
- –
- Context
- 131k
- Full answer
- –
- Cost per run
- –
- Released
- 12 Dec 2024
- Overall index42
- Reasoning37
- Coding32
- Maths41
- Knowledge45
- Human preference50
- Composite37
Versions
SpaceXAI has shipped 11 models under this name. Each is ranked on its own results; a newer version often has fewer results so far, which holds its index nearer the average until more arrive.
| Model | Released | Index | Rank |
|---|---|---|---|
| Grok 4.7high | 21 Sept 2026 | 63.9 | #59 |
| Grok 4.6medium | 11 Aug 2026 | 64.2 | #56 |
| Grok 4.5high | 8 Jul 2026 | 59.3 | #134 |
| Grok 4.3medium | 17 Apr 2026 | 58.7 | #147 |
| Grok 4.2high | 10 Mar 2026 | – | – |
| Grok 4.20thinking | 17 Feb 2026 | 58.6 | #148 |
| Grok 4.1 | 17 Nov 2025 | 57.2 | #184 |
| Grok 4 | 9 Jul 2025 | 58.0 | #162 |
| Grok 3 | 17 Feb 2025 | 51.5 | #339 |
| Grok 2this page | 12 Dec 2024 | 41.9 | #612 |
| Grok 4.20 1 | – | – | – |
How its index has moved
8 Sept 2026 to 18 Oct 2026The index is recomputed from scratch every day, so a line moves when a new benchmark result lands, when a publisher revises a score, or when the models it is normalised against change. Early movement usually means the score is still settling.
Benchmark results
See all LLM benchmarks. One column per reasoning effort. Rank is among every configuration of every model on that benchmark. Hover a score for the run it came from.
Reasoning
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| GPQA Diamond | 53.8%#207 | Epoch AI Benchmarking Hub | |
| SimpleBench | 22.7%#78 | SimpleBench | |
| Arena Hard Prompts | 1326#235 | Arena (LMArena) | |
| GPQA Diamond (AA)not in index | 51.0%#427 | Artificial Analysis | |
| Humanity's Last Exam (AA)not in index | 3.1%#605 | Artificial Analysis | |
| GPQA Diamond (Vals)not in index | 50.8%#113 | Vals AI | |
| DTBenchnot in index | 65.2%#167 | Epoch AI Benchmarking Hub |
Coding
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| WeirdML | 22.2%#139 | WeirdML | |
| Arena Coding | 1358#234 | Arena (LMArena) | |
| LiveCodeBench | 38.7%#125 | Vals AI |
Agents & tools
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| BrowseCompnot in index | 1.0%#16 | OpenAI |
Maths
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| OTIS Mock AIME | 11.5%#228 | Epoch AI Benchmarking Hub | |
| MATH Level 5 | 63.5%#44 | Epoch AI Benchmarking Hub | |
| AIME (Vals) | 15.2%#81 | Vals AI | |
| MGSM | 86.2%#61 | Vals AI | |
| MATH 500not in index | 78.4%#40 | Vals AI | |
| Arena Maths | 1294#234 | Arena (LMArena) |
Knowledge
Instruction following
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| Arena Instruction Followingnot in index | 1312#228 | Arena (LMArena) |
Human preference
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| Arena Text | 1336#218 | Arena (LMArena) | |
| Arena Creative Writingnot in index | 1317#197 | Arena (LMArena) | |
| Arena Multi-turnnot in index | 1324#220 | Arena (LMArena) | |
| Arena Longer Queriesnot in index | 1336#220 | Arena (LMArena) | |
| Lech Mazur Creative Writingnot in index | 63.6%#37 | Lech Mazur |
Composite
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| Epoch Capabilities Indexnot in index | 130.5#144 | Epoch AI Benchmarking Hub | |
| AA Intelligence Index v4.3.2 | 7.1#494 | Artificial Analysis |
See also
Questions people ask
- What are Grok 2's benchmark scores?
- As of 25 Oct 2026, Grok 2 scores 41.9 ±4.5 on the BenchLeader Index, strongest in human preference (50) and weakest in coding (32). That rests on 17 independent benchmark results, and every score on this page links to its publisher.
- How does Grok 2 rank?
- Grok 2 is #612 of 785 ranked configurations on 25 Oct 2026. 303 other configurations score within its margin, so the exact position matters less than the band. The leader is Claude Opus 5.5 (max effort) at 72.6.
- When was Grok 2 released?
- SpaceXAI released Grok 2 on 12 Dec 2024.
Data as of 25 Oct 2026. Compare with another model.
Cite as: BenchLeader, “Grok 2: benchmarks, pricing, speed and rank”, data as of 25 Oct 2026, https://www.benchleader.com/models/grok-2.