CodeAct v1.8: benchmark scores, price and ranking
CodeAct v1.8 from Anthropic ranks #200 of 743 LLMs on the LLMs Tiger aggregate benchmark score (50.3), based on 1 benchmark results captured up to 2026-10-13.
- Organisation
- Anthropic
- Type
- Frontier model
- Open weights
- No
- Aggregate rank
- #200 of 743 (score 50.3)
Across the 1 benchmark where at least ten models are scored, CodeAct v1.8 is in the top 10% on 0 and in the top half on 1.
CodeAct v1.8 benchmark results
| Benchmark | Score | Rank | Source | Captured |
|---|---|---|---|---|
| SWE-bench Lite | 26.7% | #9 of 20 | SWE-bench Lite leaderboard | 2026-10-13 |
About CodeAct v1.8
CodeAct v1.8 is a frontier model from Anthropic. No API price is listed for it yet. We hold 1 benchmark result for it across 1 area, and none is in the top tenth of its board.
Where CodeAct v1.8 stands
On our aggregate score, CodeAct v1.8 is #200 of 743 ranked models, around the middle of the table. Its score is 50.3; the scale is centred on 50, so it sits 0.3 points above the typical model. That beats 73% of the ranked field. Among the 70 ranked Anthropic models it is #35. The next one up is claude-opus-4-5-20251101-thinking-64k-high-effort at 50.3. The next one down is Claude Sonnet 4.6 (max) at 50.0.
CodeAct v1.8, benchmark by benchmark
SWE-bench Lite puts CodeAct v1.8 at 26.7%, #9 of 20. That beats 55% of the models tested, but 30.0 points short of Claude 4 Sonnet (56.7%). The results either side are Claude 3.5-Sonnet-20241022 (30.0%) and GPT-4o (24.7%). It covers real GitHub issues resolved. The board median is 24.7%, so CodeAct v1.8 is 2.0 points above it. Source: SWE-bench Lite leaderboard, captured 2026-10-13.
Reading these numbers
The 1 score on this page comes from 1 source: SWE-bench Lite leaderboard (1). 1 of them come from an official leaderboard and 0 from datasets or third-party runs. With 1 results the aggregate rank can move a lot when one new score arrives.
Models ranked nearby
- #197 Claude 4.5 Haiku (50.3)
- #198 claude-opus-4-5-20251101-thinking-64k-high-effort (50.3)
- #199 Grok Build + Grok 4.7 (50.3)
- #201 Codex + GPT-5.6 Sol (50.3)
- #202 DeepSeek V3.2 Reasoner (50.3)
- #203 chatgpt-4o-latest (2025-03-29) (50.2)
More from Anthropic
- Claude Opus 5.5 (max) (#1, 64.3)
- Claude Fable 5.1 (max) (#3, 61.9)
- Claude Sonnet 5.5 (max) (#4, 60.8)
- Claude Opus 5 (max) (#8, 60.0)
- Claude Fable 5 (max) (#9, 59.9)
- claude-opus-4-8-xhigh-effort (#14, 56.6)
Compare it on the live leaderboard → · How the aggregate score works