Long Context · sub-raceNarrow lead
Long-Document Reasoning race
Synthesising answers that depend on details scattered across a huge document.
- Leader
- Gemini 4 Argon
- Margin
- 0.6 pts
- 0.7% ahead
- Weeks at #1
- 1
- in a row
- Changes
- 5
- in 2026
Warming up the track…
Oct 19, 2026Gemini 4 Argon leads
2025Apr ’25Jul ’25Oct ’252026Apr ’26Jul ’26Oct ’26
Score history
Top 6 today over the leader's frontier · click to jump to a week
#1 frontierGemini 4 ArgonGPT-6 AstraFable 5.1Opus 5.5GPT-6.1 SolMuse Wonder
Reigns at #1
Longest: 2.5 Pro, 33 weeks (from Mar 2025).
Sibling races
More long context races
Why this race matters
Real long-context work is synthesis, not lookup.
How it is scored
Accuracy at 128K+ tokens.
Unit: percentHigher is betterPhoto finish under 0.5 ptsDominant over 3.0 pts
Data provenance
Fiction.LiveBench / LongBench v2
Questions requiring whole-document understanding.
Scores here are illustrative placeholders that mimic real benchmark patterns. Swap in live data through the score provider. Methodology