Home  /  League  /  Fixtures  /  Claude Haiku 5.5 vs Gemini 4 Neon
League fixture

Claude Haiku 5.5 vs Gemini 4 Neon.

Value champion vs League leader — decided by the data: category winners, tale of the tape and head-to-head benchmarks.

VS
Google DeepMind

League fixture: Value champion vs League leader. In Season Zero, fixture results are decided by the data — the category winners above. When voted fixtures launch, results blend 60% benchmark / 40% crowd per the published rulebook.

Verdict by category

CategoryClaude Haiku 5.5Gemini 4 NeonWinner
League Score66.4100.0Gemini 4 Neon
Coding (SWE-bench %)———
Reasoning (GPQA %)———
Context (tokens)10000001048576Gemini 4 Neon
Speed (tok/s)———
Price (blended $/1M)$0.20$6.00Claude Haiku 5.5 (cheaper)

Tale of the tape

SpecClaude Haiku 5.5Gemini 4 Neon
MakerAnthropicGoogle DeepMind
ReleasedOct 7, 2026Nov 18, 2026
League Score66100
Context1,000,000 tokens1,048,576 tokens
Max output128,0001,048,576
$/1M input$0.10$3.00
$/1M output$0.50$15.00
WeightsClosedClosed
Speed——

Head-to-head benchmarks (shared only)

BenchmarkClaude Haiku 5.5Gemini 4 Neon
LiveBench overall68.987.4

Cost at three workloads

WorkloadClaude Haiku 5.5Gemini 4 Neon
Light — 1M in / 250K out$0.23$6.75
Standard — 10M in / 2.5M out$2.25$67.50
Long-context — 50M in / 5M out$7.50$225.00

The pick

Pick Claude Haiku 5.5 if you want the lower running cost.

Pick Gemini 4 Neon if you want the higher overall League Score; you need the bigger context window.

All figures from the model database — sources and dates on each model page. Cost your own workload or compare a different pair.