Benchmark profile
LisanBench
A word-chain reasoning benchmark that tests planning, recall, constraint following, and vocabulary depth by asking models to extend non-repeating edit-distance-1 chains.
How BenchLM shows LisanBench
BenchLM mirrors the current public LisanBench difficulty-weighted leaderboard using the official dataset published at lisanbench.com for the July 21, 2026 snapshot. The public benchmark tests 150 model variants across 50 starting words, with 3 trials per starting word.
LisanBench is a strong reasoning reference, but BenchLM currently keeps it display only rather than weighted. The public leaderboard is highly variant-specific, strongly English-vocabulary-dependent, and not yet aligned cleanly enough with BenchLM canonical model rows to use as a ranking input.
Difficulty-weighted score on LisanBench — July 21, 2026 snapshot
BenchLM mirrors the published difficulty-weighted score view for LisanBench. Opus 4.7 (xhigh) leads the public snapshot at 5122.60 , followed by Claude Fable 5 (medium) (4561.82) and Opus 4.6 (16k) (3526.49). BenchLM does not use these results to rank models overall.
Opus 4.7 (xhigh)
Anthropic
anthropic/claude-opus-4.7:thinking-xhigh
Claude Fable 5 (medium)
Anthropic
anthropic/claude-fable-5:thinking-medium
Opus 4.6 (16k)
Anthropic
anthropic/claude-opus-4.6:thinking-16k
Difficulty-weighted score table (150 models)
ScoreThe published LisanBench snapshot places Opus 4.7 (xhigh) first at 5122.60. The third row is 1596.11 score units behind. The broader top-10 range is 3344.20 score units, so the table still separates the published systems.
150 models have been evaluated on LisanBench. The benchmark falls in the Reasoning category. This category carries a 17% weight in BenchLM.ai's overall scoring system. LisanBench is currently displayed for reference but excluded from the scoring formula, so it does not directly affect overall rankings.
About LisanBench
Year
2026
Tasks
50 starting words × 3 trials
Format
Difficulty-weighted word-chain reasoning
Difficulty
Open-ended lexical planning
BenchLM mirrors the public difficulty-weighted LisanBench leaderboard as a display-only reasoning benchmark. The public benchmark currently evaluates 128 model variants across 50 starting words with 3 trials per word.
BenchLM freshness & provenance
Version
LisanBench 2026
Refresh cadence
Static
Staleness state
Current
Question availability
Public benchmark set
BenchLM uses freshness metadata to decide whether a benchmark should still be treated as a strong differentiator, a benchmark to watch, or a display-only reference. For the full scoring policy, see the BenchLM methodology page.
FAQ
What does LisanBench measure?
A word-chain reasoning benchmark that tests planning, recall, constraint following, and vocabulary depth by asking models to extend non-repeating edit-distance-1 chains.
Which model leads the published LisanBench snapshot?
Opus 4.7 (xhigh) currently leads the published LisanBench snapshot with 5122.60 difficulty-weighted score. BenchLM shows this benchmark for display only and does not use it in overall rankings.
How many models are evaluated on LisanBench?
150 AI models are included in BenchLM's mirrored LisanBench snapshot, based on the public leaderboard captured on July 21, 2026 snapshot.
Choose a model with this week’s evidence
Join 2,000+ readers for ranking moves, pricing changes, and the claims that still need proof.
One email each week. Unsubscribe anytime.