Claude 3 Opus: benchmark scores, price and ranking
Claude 3 Opus from Anthropic ranks #559 of 743 LLMs on the LLMs Tiger aggregate benchmark score (45.7), based on 4 benchmark results captured up to 2026-10-14.
- Organisation
- Anthropic
- Type
- Frontier model
- Open weights
- No
- Released
- 2024-03-04 (source: curated)
- Cheapest API price
- $15.00 in / $75.00 out per million tokens (via vercel_ai_gateway, observed 2026-10-14T22:47Z)
- Aggregate rank
- #559 of 743 (score 45.7)
Relative to other models, Claude 3 Opus is strongest on Epoch ECI (#106 of 204) and weakest on SWE-bench Verified (#67 of 73).
Across the 4 benchmarks where at least ten models are scored, Claude 3 Opus is in the top 10% on 0 and in the top half on 0.
Its cheapest listed input price, $15.00 per million tokens, is lower than that of 2% of the 427 models with a listed price.
Claude 3 Opus benchmark results
| Benchmark | Score | Rank | Source | Captured |
|---|---|---|---|---|
| Epoch ECI | 127 | #106 of 204 | Epoch AI Benchmarking Hub | 2026-10-14 |
| SWE-bench Test | 10.5% | #7 of 11 | SWE-bench Test leaderboard | 2026-10-14 |
| SWE-bench Lite | 11.7% | #16 of 20 | SWE-bench Lite leaderboard | 2026-10-14 |
| SWE-bench Verified | 15.8% | #67 of 73 | SWE-bench Verified leaderboard | 2026-10-14 |
About Claude 3 Opus
Claude 3 Opus is a frontier model from Anthropic. It was released on 2024-03-04, according to the developer's announcement. The cheapest API listing we track charges $15.00 per million input tokens and $75.00 per million output tokens, through vercel_ai_gateway. We hold 4 benchmark results for it across 2 areas, and none is in the top tenth of its board.
Where Claude 3 Opus stands
On our aggregate score, Claude 3 Opus is #559 of 743 ranked models, in the lower half. Its score is 45.7; the scale is centred on 50, so it sits 4.3 points below the typical model. That beats 25% of the ranked field. Among the 70 ranked Anthropic models it is #60. The next one up is claude-instant-1.2 at 45.8. The next one down is Claude 3.5 Sonnet (Oct 2024) at 45.4.
Claude 3 Opus, benchmark by benchmark
Claude 3 Opus lands below the middle on Epoch ECI: 127, #106 of 204, with 51% of the field scoring higher. Qwen 3.8 Max leads at 156; the closest result above is Mistral Small 3 at 127. It covers Epoch Capabilities Index: Epoch's own aggregate of ~40 benchmarks. The board median is 127, so Claude 3 Opus is 0 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-14.
Claude 3 Opus lands below the middle on SWE-bench Test: 10.5%, #7 of 11, with 55% of the field scoring higher. Claude 4.5 Opus leads at 52.6%; the closest result above is GPT-4 (1106) at 12.5%. It covers real GitHub issues resolved. The board median is 12.5%, so Claude 3 Opus is 2.0 points below it. Source: SWE-bench Test leaderboard, captured 2026-10-14.
Claude 3 Opus lands below the middle on SWE-bench Lite: 11.7%, #16 of 20, with 75% of the field scoring higher. Claude 4 Sonnet leads at 56.7%; the closest result above is MCTS Refine 7B at 16.3%. It covers real GitHub issues resolved. The board median is 24.7%, so Claude 3 Opus is 13.0 points below it. Source: SWE-bench Lite leaderboard, captured 2026-10-14.
SWE-bench Verified is a weak spot. Claude 3 Opus scores 15.8%, #67 of 73, behind 90% of the models measured. The leader, Claude Opus 4.7 (max), reaches 83.5%. It covers real GitHub issues resolved. The board median is 56.4%, so Claude 3 Opus is 40.6 points below it. Source: SWE-bench Verified leaderboard, captured 2026-10-14.
Strengths and weaknesses
Software engineering: weak, ahead of 14% of the field on average across 2 benchmarks. Its best board here is SWE-bench Lite (#16 of 20) and its weakest is SWE-bench Verified (#67 of 73). General knowledge and chat: uneven, ahead of 42% of the field on average across 2 benchmarks. Its best board here is Epoch ECI (#106 of 204) and its weakest is SWE-bench Test (#7 of 11).
Price and value
The median input price across the 427 priced models is $0.500 per million tokens, so Claude 3 Opus costs more than the typical listing. Models that score within 1.5 points or better and cost less: DeepSeek V4.1 Flash (high) ($0.010, 49.7), Qwen2.5-Coder-7B-Instruct ($0.010, 49.5), Qwen2.5-Coder-3B-Instruct ($0.010, 46.5). Similar scores cost more on GPT-4 (1106) ($30.00) and GPT-4.5 Preview (Feb 2025) ($75.00).
Release history
The Anthropic model released before it was claude-2.1 on 2023-11-21, which scores 40.5. The next one was claude-3-opus-20240229 on 2024-03-04, at 43.2.
Reading these numbers
The 4 scores on this page come from 4 sources: Epoch AI Benchmarking Hub (1), SWE-bench Lite leaderboard (1), SWE-bench Test leaderboard (1), SWE-bench Verified leaderboard (1). 3 of them come from an official leaderboard and 1 from datasets or third-party runs. With 4 results the aggregate rank can move a lot when one new score arrives.
Models ranked nearby
- #556 claude-instant-1.2 (45.8)
- #557 MiniMax-M2.7 (45.8)
- #558 Mistral-Nemo-Base-2407 (45.8)
- #560 amazon.nova-lite-v1:0 (45.7)
- #561 qwen1.5-32b-chat (45.7)
- #562 EXAONE-3.5-2.4B-Instruct (45.7)
More from Anthropic
- Claude Opus 5.5 (max) (#1, 64.2)
- Claude Fable 5.1 (max) (#4, 61.8)
- Claude Sonnet 5.5 (max) (#5, 60.9)
- Claude Opus 5 (max) (#7, 60.0)
- Claude Fable 5 (max) (#10, 59.8)
- claude-opus-4-8-xhigh-effort (#14, 56.6)
Compare it on the live leaderboard → · How the aggregate score works