Grok 4.5
Grok 4.5 (xAI) was released on Jul 8, 2026. In the Epoch AI capability ranking (ECI), it ranks #41 out of 267 models, with 153.93. On Arena, which measures human preference in blind comparisons, it has 1,495 ELO points (#60). On LiveBench, the overall average is 75.8, #28 out of 58 scored models. Against models of the same generation, its best result is on Dtbench: 96.5%, #10 of 70, tied with 1 others.
Where Grok 4.5 stands out and where it falls behind, by the numbers
Grok 4.5 has published results on 27 tests compiled by Epoch AI. The yardstick here is its generation: its position among the models released between Oct 11, 2025 and Oct 6, 2026 that took the same test. Against the whole archive, which includes 2023 models, a recent release lands near the top of almost everything, and that says nothing.
Where it stands out
Tests where it sits in the top third of its own generation.
Where it falls behind
Tests where it sits in the bottom half of its own generation.
See all 27 tests, one by one
| Test | Score | In its generation | Overall | Test record |
|---|---|---|---|---|
| GPQA Diamond | 93.4% | #16 / 80 | #16 / 173 | 96.4% Gemini 4 Argon |
| AIME 2024 and 2025 (OTIS) | 97.8% | #26 / 81 (tied with 1) | #29 / 168 | 100.0% GPT-5.5 |
| Dtbench | 96.5% | #10 / 70 (tied with 1) | #10 / 148 | 98.9% Claude Opus 5.5 |
| Lmca | 45.20 | #33 / 70 | #33 / 121 | 68.23 Claude Opus 5.5 |
| CritPt | 15.4% | #34 / 78 (tied with 1) | #36 / 112 | 32.3% GPT-5.6 Sol |
| WeirdML | 46.4% | #44 / 55 | #54 / 112 | 93.6% GPT-6 Astra |
| SciCode | 55.0% | #25 / 75 (tied with 1) | #26 / 104 | 66.9% Claude Opus 5.5 |
| Frontiermath Tiers 1 3 V2 | 57.2% | #40 / 65 (tied with 1) | #43 / 86 | 93.7% GPT-6 Astra |
| ARC-AGI 2 | 52.6% | #35 / 51 | #35 / 83 | 95.0% GPT-6 Astra |
| ALE-Bench | 1,309 | #21 / 65 | #21 / 82 | 2,951 GPT-6 Astra |
| WebDev Arena | 1,555 | #30 / 76 | #30 / 82 | 1,820 Claude Opus 5.5 |
| ARC-AGI | 87.2% | #33 / 51 | #33 / 81 | 98.5% Claude Fable 5 |
| SimpleQA Verified | 48.3% | #27 / 63 | #31 / 81 | 76.0% Gemini 4 Argon |
| Chess puzzles | 35.0% | #38 / 64 | #42 / 80 | 76.0% GPT-6 Astra |
| ProofBench | 31.0% | #40 / 68 (tied with 1) | #42 / 74 | 100.0% Claude Fable 5.1 |
| SimpleBench | 70.0% | #12 / 38 | #12 / 74 | 81.9% Claude Fable 5 |
| Frontiermath Tier 4 V2 | 24.4% | #38 / 55 (tied with 1) | #41 / 67 | 100.0% GPT-6.1 Sol |
| Vending Bench 2 | 3,887 | #36 / 48 | #37 / 57 | 15,515 GPT-6 Astra |
| Apex Agents | 56.2% | #17 / 48 | #17 / 50 | 82.4% Gemini 4 Argon |
| FrontierCode | 42.4% | #20 / 42 | #21 / 43 | 54.6% Claude Opus 5.5 |
| Gdp Pdf | 14.0% | #29 / 36 (tied with 3) | #30 / 37 | 35.0% GPT-6.1 Sol |
| Furniture Assembly | 22.5% | #28 / 32 | #30 / 34 | 83.3% Claude Opus 5.5 |
| Blueprint Bench 2 | 27.3% | #18 / 30 | #19 / 31 | 54.4% Gemini 4 Argon |
| DeepSWE | 53.8% | #18 / 26 | #18 / 26 | 74.1% GPT-6 Astra |
| Surface Evolver Bench | 74.4% | #8 / 23 | #8 / 24 | 95.0% Claude Fable 5 |
| Gbaeval | 65.4% | #4 / 22 | #4 / 22 | 79.6% Claude Opus 5 |
| Posttrainbench | 23.5% | #9 / 11 | #9 / 11 | 41.8% Claude Fable 5 |
For each test, the model's best effort level counts, as in the ranking. Source of the scores: Epoch AI, under CC BY 4.0.
What to compare Grok 4.5 with
The models from other labs closest in capability and released in the same period, at most two per lab. Click any of them to see its page.
| Model | Lab | ECI | ELO | LiveBench | Release |
|---|---|---|---|---|---|
| DeepSeek V4 Flash 0731 | DeepSeek | 154.49 | n/a | 74.2 | Jul 31, 2026 |
| Gemini 3.5 Flash | Google DeepMind | 154.38 | 1,526 | 74.6 | May 19, 2026 |
| Gemini 3.6 Flash | Google DeepMind | 154.24 | 1,530 | 73.6 | Jul 21, 2026 |
| Muse Spark 1.1 | Meta AI | 154.00 | 1,516 | 75.3 | Jul 9, 2026 |
| Grok 4.5 | xAI | 153.93 | 1,495 | 75.8 | Jul 8, 2026 |
| Qwen3.7-Max | Alibaba | 153.83 | 1,530 | 73.1 | May 19, 2026 |
| GPT-5.2 | OpenAI | 153.46 | 1,454 | 74.6 | Dec 11, 2025 |
Grok 4.5 or Muse Spark 1.1?
Muse Spark 1.1 is the model from another lab closest to Grok 4.5 in capability. Across the 13 tests both took, this is the score:
| Test | Grok 4.5 | Muse Spark 1.1 |
|---|---|---|
| Gbaeval | 65.4% | 7.9% |
| Apex Agents | 56.2% | 31.8% |
| Vending Bench 2 | 3,887 | 6,520 |
| Surface Evolver Bench | 74.4% | 52.5% |
| ProofBench | 31.0% | 39.0% |
| SimpleQA Verified | 48.3% | 57.8% |
| Lmca | 45.20 | 49.91 |
| Gdp Pdf | 14.0% | 15.0% |
| SciCode | 55.0% | 58.8% |
| Dtbench | 96.5% | 94.4% |
Unweighted score: each test counts one point, whether math or coding. The dot marks who did better on each row.
What Grok 4.5 costs to deliver each task
Price per token is what is on the price sheet; cost per task is what lands on the invoice, because it depends on how many tokens the model spends. Each point is an effort level, published by whoever ran the test and compiled by Epoch AI. The further up and to the left, the more score per dollar.
ARC-AGI 2
The score scale does not start at zero.
ARC-AGI
The score scale does not start at zero.
Other models from xAI
The models from the same lab closest in time, newest first.
| Model | Release | ECI | ELO | LiveBench | Access |
|---|---|---|---|---|---|
| Grok 4.7 | Sep 21, 2026 | 154.37 | 1,453 | 77.4 | API access |
| Grok 4.6 | Aug 12, 2026 | 156.31 | 1,475 | 78.0 | API access |
| Grok 4.5 | Jul 8, 2026 | 153.93 | 1,495 | 75.8 | API access |
| Grok 4.3 (no thinking) | Apr 17, 2026 | 149.21 | 1,425 | 62.3 | Hosted access (no API) |
| Grok 4.3 Beta | Apr 17, 2026 | 148.95 | n/a | n/a | Hosted access (no API) |
| Grok 4.20 | Feb 17, 2026 | 152.08 | n/a | n/a | API access |
| Grok 4 Fast | Sep 19, 2025 | 144.19 | 1,437 | n/a | API access |
| Grok 4 | Jul 9, 2025 | 146.43 | n/a | n/a | API access |
| Grok-3 mini | Jun 24, 2025 | 140.33 | 1,394 | n/a | API access |
Have you used Grok 4.5? Rate it
Users' opinion, not measurement: the rating is kept apart from the ranking and does not move anyone's position. One vote per browser, no sign-up, and you can change your rating later.
What people ask about Grok 4.5
Where does Grok 4.5 rank among AI models?
In the ROO3 AI Benchmark, ordered by the Epoch AI ECI, Grok 4.5 ranks #41 out of 267 models, with an ECI of 153.93. The ECI is a composite index that combines several hard benchmarks into a single scale. The position changes when a new model comes out, and the page is refreshed six times a day.
Is Grok 4.5 better than Muse Spark 1.1?
Across the 13 tests both models took and Epoch AI compiled, Grok 4.5 comes out ahead on 7, behind on 6 and tied on 0. It is a test-by-test count with no weighting: a win in math counts the same as a win in coding. To choose between the two, look at the tests that resemble your own use.
What is Grok 4.5 best at?
Against models of the same generation (released up to 9 months before and up to 3 months after it), the best relative results of Grok 4.5 are: Dtbench (#10 of 70); Gbaeval (#4 of 22); GPQA Diamond (#16 of 80). The yardstick is its position among the models of that period that took the same test.
Where do the numbers on this page come from?
From the same three sources as the ranking, all openly licensed: Epoch AI (ECI and individual tests, CC BY 4.0), Arena (human-preference ELO, CC BY 4.0) and LiveBench (overall average, CC BY-SA 4.0). ROO3 does not measure any model. When the page shows a figure published by the maker itself, it appears in the written analysis, labeled as the maker's, and never enters the ranking.
Where each number comes from
Epoch AI, "AI Benchmarking Hub". Published at epoch.ai. Data under the CC BY 4.0 licence, reordered by roo3.co.
The Arena (LMArena) leaderboard, from the public lmarena-ai/leaderboard-dataset on Hugging Face, under the CC BY 4.0 licence. We are not affiliated with the Arena.
LiveBench, by the LiveBench team, published at livebench.ai under the CC BY-SA 4.0 license. The overall average is recomputed by roo3.co with the same formula as the website (average of the categories), and those numbers stay under CC BY-SA 4.0. We are not affiliated with LiveBench.
← See the full ranking