LiveBench Language leaderboard: which LLMs score highest
LiveBench Language (LiveBench release 2026_06_25) currently has scores for 17 models. The top score is 87.4% by GPT-5.5 (xhigh); the median model scores 77.9% and the lowest scores 62.5%.
| # | Model | Organisation | LiveBench Language score | Cheapest input $/M | Source | Captured |
|---|---|---|---|---|---|---|
| 1 | GPT-5.5 (xhigh) | OpenAI | 87.4% | $5.00 | LiveBench 2026_06_25 official CSV | 2026-10-05 |
| 2 | gemini-3.1-pro-preview-high | 85.4% | $2.00 | LiveBench 2026_06_25 official CSV | 2026-10-05 | |
| 3 | gemini-3.5-flash-high | 84.6% | $1.50 | LiveBench 2026_06_25 official CSV | 2026-10-05 | |
| 4 | GPT-5.4 (xhigh) | OpenAI | 82.6% | $2.50 | LiveBench 2026_06_25 official CSV | 2026-10-05 |
| 5 | claude-opus-4-8-xhigh-effort | Anthropic | 81.4% | $5.00 | LiveBench 2026_06_25 official CSV | 2026-10-05 |
| 6 | claude-opus-4-5-20251101-thinking-64k-high-effort | Anthropic | 81.3% | $5.00 | LiveBench 2026_06_25 official CSV | 2026-10-05 |
| 7 | gpt-5.2-2025-12-11-high | OpenAI | 79.8% | $1.75 | LiveBench 2026_06_25 official CSV | 2026-10-05 |
| 8 | Qwen3.7 Max | Alibaba | 79.7% | $1.25 | LiveBench 2026_06_25 official CSV | 2026-10-05 |
| 9 | Kimi K2.7 Code | Moonshot | 77.9% | $0.671 | LiveBench 2026_06_25 official CSV | 2026-10-05 |
| 10 | MiniMax-M3 | MiniMax | 76.8% | $0.230 | LiveBench 2026_06_25 official CSV | 2026-10-05 |
| 11 | kimi-k2.6-thinking | Moonshot AI | 75.1% | $0.650 | LiveBench 2026_06_25 official CSV | 2026-10-05 |
| 12 | qwen3.6-plus | Alibaba | 75.0% | $0.325 | LiveBench 2026_06_25 official CSV | 2026-10-05 |
| 13 | GPT-5.2 Codex | OpenAI | 73.7% | $1.75 | LiveBench 2026_06_25 official CSV | 2026-10-05 |
| 14 | grok-build-0.1 | xAI | 72.5% | $1.00 | LiveBench 2026_06_25 official CSV | 2026-10-05 |
| 15 | GPT-5.4 mini (xhigh) | OpenAI | 71.0% | $0.750 | LiveBench 2026_06_25 official CSV | 2026-10-05 |
| 16 | Qwen3.6 27B | Alibaba | 63.3% | $0.150 | LiveBench 2026_06_25 official CSV | 2026-10-05 |
| 17 | GPT-5.4 nano (xhigh) | OpenAI | 62.5% | $0.200 | LiveBench 2026_06_25 official CSV | 2026-10-05 |
Compare all benchmarks side by side on the live leaderboard →
Among the ten highest scorers, the cheapest listed API price belongs to MiniMax-M3 at $0.230 per million input tokens (score 76.8%).
What LiveBench Language measures
LiveBench Language measures LiveBench release 2026_06_25.
How to read these scores
Scores are percentages (higher is better): the share of questions or tasks the model completed correctly. Where a model is listed at several reasoning efforts, only its highest-effort row is shown. See the methodology for how rows are chosen.
Where the data comes from
LiveBench 2026_06_25 official CSV. Scores were last captured 2026-10-05; the Captured column gives each row's date.