Skip to main content
BenchLM
Advertise

Benchmark profile

LongBench v2

A long-context benchmark that measures whether models can actually use extended context windows for reasoning and retrieval.

Data verified

Top models on LongBench v2 — July 23, 2026

As of July 23, 2026, Claude Opus 4.5 leads the LongBench v2 leaderboard with 64.4% , followed by Qwen3.5 397B (63.2%) and Qwen3.6 Plus (62%).

1Closed

Claude Opus 4.5

Anthropic

claude-opus-4-5

64.4%
Overall 64.22Context 200K
2Open

Qwen3.5 397B

Alibaba

qwen3-5-397b

63.2%
Overall 57.01Context 128K
3Closed

Qwen3.6 Plus

Alibaba

qwen3-6-plus

62%
Overall 65.2Context 1M
12 modelsReasoning38% of category scoreCurrentUpdated July 23, 2026

Leaderboard (12 models)

Score
1
Claude Opus 4.5Anthropic · Closed
64.4%
2
Qwen3.5 397BAlibaba · Open weight
63.2%
3
Qwen3.6 PlusAlibaba · Closed
62%
4
Nemotron 3 UltraNVIDIA · Open weight
61.9%
5
Kimi K2.5Moonshot AI · Open weight
61%
6
GLM-5Z.AI · Open weight
60.8%
7
Qwen3.5-27BAlibaba · Open weight
60.6%
8
Qwen3.5-122B-A10BAlibaba · Open weight
60.2%
9
Agents-A1InternScience · Open weight
60.2%
10
Qwen3.5-35B-A3BAlibaba · Open weight
59%
11
DeepSeek V4 Pro BaseDeepSeek · Open weight
51.5%
12
DeepSeek V4 Flash BaseDeepSeek · Open weight
44.7%

According to BenchLM.ai, Claude Opus 4.5 leads the LongBench v2 benchmark with a score of 64.4%, followed by Qwen3.5 397B (63.2%) and Qwen3.6 Plus (62%). The top models are clustered within 2.4 points, suggesting this benchmark is nearing saturation for frontier models.

12 models have been evaluated on LongBench v2. The benchmark falls in the Reasoning category. This category carries a 17% weight in BenchLM.ai's overall scoring system. Within that category, LongBench v2 contributes 38% of the category score, so strong performance here directly affects a model's overall ranking.

About LongBench v2

Year

2025

Tasks

Long-context tasks

Format

Extended-context retrieval and reasoning

Difficulty

Hard long-context

LongBench v2 is useful because context-window size alone is not a capability. It measures whether a model can retain, retrieve, and reason over long inputs effectively.

LongBench v2

BenchLM freshness & provenance

Version

LongBench v2 2025

Refresh cadence

Quarterly

Staleness state

Current

Question availability

Public benchmark set

Current

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 LongBench v2 measure?

A long-context benchmark that measures whether models can actually use extended context windows for reasoning and retrieval.

Which model scores highest on LongBench v2?

Claude Opus 4.5 by Anthropic currently leads with a score of 64.4% on LongBench v2.

How many models are evaluated on LongBench v2?

12 AI models have been evaluated on LongBench v2 on BenchLM.

Compare Top Models on LongBench v2

Claude Opus 4.5 vs Qwen3.5 397BQwen3.5 397B vs Qwen3.6 PlusQwen3.6 Plus vs Nemotron 3 UltraNemotron 3 Ultra vs Kimi K2.5
Last updated: July 23, 2026 · BenchLM version LongBench v2 2025

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.