Claude 3.5 Sonnet (October 2024)
Claude 3.5 Sonnet (October 2024) (Anthropic) was released on Oct 22, 2024. In the Epoch AI capability ranking (ECI), it ranks #152 out of 267 models, with 133.53. On Arena, which measures human preference in blind comparisons, it has 1,342 ELO points (#230). Against models of the same generation, its best result is on BALROG: 32.6%, #1 of 16.
Where Claude 3.5 Sonnet (October 2024) stands out and where it falls behind, by the numbers
Claude 3.5 Sonnet (October 2024) has published results on 24 tests compiled by Epoch AI. The yardstick here is its generation: its position among the models released between Jan 26, 2024 and Jan 20, 2025 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 24 tests, one by one
| Test | Score | In its generation | Overall | Test record |
|---|---|---|---|---|
| GPQA Diamond | 55.3% | #6 / 37 | #124 / 173 | 96.4% Gemini 4 Argon |
| AIME 2024 and 2025 (OTIS) | 8.5% | #10 / 32 (tied with 1) | #135 / 168 | 100.0% GPT-5.5 |
| Dtbench | 67.8% | #2 / 28 | #95 / 148 | 98.9% Claude Opus 5.5 |
| WeirdML | 40.0% | #2 / 20 | #72 / 112 | 93.6% GPT-6 Astra |
| MMLU | 87.3% | #2 / 48 | #2 / 92 | 88.1% GPT-4o (May 2024) |
| SimpleBench | 41.4% | #2 / 13 | #48 / 74 | 81.9% Claude Fable 5 |
| MATH level 5 | 56.9% | #9 / 34 | #38 / 73 | 98.1% GPT-5 |
| FrontierMath | 2.1% | #2 / 8 | #52 / 65 | 51.7% GPT-5.5 |
| ForecastBench | 60.70 | #1 / 14 | #20 / 62 | 62.50 o3 |
| FrontierMath tier 4 | 0.0% | #1 / 1 | #40 / 48 | 39.6% GPT-5.5 Pro |
| Hle | 4.1% | #4 / 5 | #38 / 39 | 54.8% GPT-6 Astra |
| Aider Polyglot | 51.60 | #2 / 6 | #22 / 38 | 88.00 GPT-5 |
| Creative writing (Lech Mazur) | 8.03 | #2 / 10 | #14 / 38 | 8.60 GPT-5 |
| EnigmaEval | 0.9% | #2 / 5 | #31 / 36 | 39.3% Claude Fable 5 |
| BALROG | 32.6% | #1 / 16 | #15 / 32 | 68.3% GPT-6 Astra |
| LiveBench | 59.03 | #2 / 18 | #13 / 32 | 82.35 Gemini 2.5 Pro (Jun 2025) |
| METR: time horizon | 20.52 | #2 / 7 | #23 / 29 | 719 Claude Opus 4.6 |
| Gso | 4.6% | #1 / 2 | #23 / 28 | 88.2% Claude Fable 5.1 |
| GeoBench | 3,327 | #6 / 8 | #17 / 24 | 4,333 Gemini 3 Flash |
| VPCT | 33.0% | #4 / 4 | #22 / 22 | 91.0% Gemini 3 Pro |
| Cybench | 17.5% | #1 / 8 | #11 / 19 | 93.0% Claude Opus 4.6 |
| CAD-Eval | 48.0% | #2 / 6 | #7 / 14 | 74.0% o3 |
| The Agent Company | 34.4% | #1 / 8 | #6 / 14 | 52.4% DeepSeek-V3.2-Exp |
| Video Mme | 60.0% | #6 / 6 | #6 / 6 | 75.0% Gemini 1.5 Pro (Sept 2024) |
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 Claude 3.5 Sonnet (October 2024) 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 |
|---|---|---|---|---|---|
| Mistral Medium 3 | Mistral AI | 134.06 | n/a | n/a | May 7, 2025 |
| Gemini 2.5 Flash-Lite (Jun 2025) | Google DeepMind | 133.95 | n/a | n/a | Jun 17, 2025 |
| gemini-2.5-flash-lite-preview-06-17 (Default thinking length) | Google DeepMind | 133.92 | 1,401 | n/a | Jun 17, 2025 |
| Claude 3.5 Sonnet (October 2024) | Anthropic | 133.53 | 1,342 | n/a | Oct 22, 2024 |
| Magistral Small 1.0 | Mistral AI | 133.20 | n/a | n/a | Jun 10, 2025 |
| Qwen2.5-Max | Alibaba | 132.53 | 1,396 | n/a | Jan 25, 2025 |
| Llama 4 Maverick | Meta AI | 132.20 | n/a | n/a | Apr 6, 2025 |
Claude 3.5 Sonnet (October 2024) or Mistral Medium 3?
Mistral Medium 3 is the model from another lab closest to Claude 3.5 Sonnet (October 2024) in capability. Across the 7 tests both took, this is the score:
| Test | Claude 3.5 Sonnet (October 2024) | Mistral Medium 3 |
|---|---|---|
| FrontierMath | 2.1% | 0.3% |
| AIME 2024 and 2025 (OTIS) | 8.5% | 32.2% |
| MATH level 5 | 56.9% | 81.6% |
| Hle | 4.1% | 4.5% |
| Dtbench | 67.8% | 62.3% |
| GPQA Diamond | 55.3% | 59.5% |
| Creative writing (Lech Mazur) | 8.03 | 7.73 |
Unweighted score: each test counts one point, whether math or coding. The dot marks who did better on each row.
Other models from Anthropic
The models from the same lab closest in time, newest first.
| Model | Release | ECI | ELO | LiveBench | Access |
|---|---|---|---|---|---|
| Claude Opus 4.1 | Aug 5, 2025 | 144.09 | 1,479 | n/a | API access |
| Claude Opus 4 | May 22, 2025 | 142.65 | 1,442 | n/a | API access |
| Claude Sonnet 4 | May 22, 2025 | 141.67 | 1,414 | n/a | API access |
| Claude 3.7 Sonnet | Feb 24, 2025 | 141.14 | 1,360 | n/a | API access |
| Claude 3.5 Sonnet (October 2024) | Oct 22, 2024 | 133.53 | 1,342 | n/a | API access |
| Claude 3.5 Haiku | Oct 22, 2024 | 127.17 | 1,286 | n/a | API access |
| Claude 3 Haiku | Mar 7, 2024 | 118.39 | 1,206 | n/a | API access |
| Claude 3 Opus | Feb 29, 2024 | 126.91 | 1,264 | n/a | API access |
| Claude 3 Sonnet | Feb 29, 2024 | 120.72 | 1,226 | n/a | API access |
Have you used Claude 3.5 Sonnet (October 2024)? 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 Claude 3.5 Sonnet (October 2024)
Where does Claude 3.5 Sonnet (October 2024) rank among AI models?
In the ROO3 AI Benchmark, ordered by the Epoch AI ECI, Claude 3.5 Sonnet (October 2024) ranks #152 out of 267 models, with an ECI of 133.53. 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 Claude 3.5 Sonnet (October 2024) better than Mistral Medium 3?
Across the 7 tests both models took and Epoch AI compiled, Claude 3.5 Sonnet (October 2024) comes out ahead on 3, behind on 4 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 Claude 3.5 Sonnet (October 2024) 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 Claude 3.5 Sonnet (October 2024) are: BALROG (#1 of 16); ForecastBench (#1 of 14); Cybench (#1 of 8). 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