MRCR v2 8-needle 128K (average)
We haven't written a description for this benchmark yet; see the card notes below for how each maker ran it.
- ModelScoreYour cost / mo
- 1Gemini 3.1 Pro · Googlebest value84.9%
- 2Gemma 4 31B · Googlebest value66.4%
- 3Gemini 3.1 Flash-Lite · Google60.1%
- 4Gemini 2.5 Pro · Google58.0%
- 5Gemini 2.5 Flash-Lite · Googlebest value16.6%
“Best value”: no other model here reports a higher score at a lower cost for your workload. Scores are self-reported by each maker with different settings, so treat close calls as ties.
How each maker reported it
- Gemini 3.1 Pro p.4
Results as of February 2026, Gemini at Thinking (High); competitors at their highest reported settings, as listed by Google.
- Gemma 4 31B Benchmark results
Instruction-tuned models, as published in Google's model card. OmniDocBench is edit distance (lower is better). Audio benchmarks are omitted because 31B has no audio input.
- Gemini 3.1 Flash-Lite p.4 (table also on the model card web page)
Results as of March 2026, as published in Google's model card. Settings as labelled by Google: 3.1 Flash-Lite High, 2.5 Flash and 2.5 Flash-Lite Dynamic, GPT-5 mini High, Claude 4.5 Haiku Extended Thinking, Grok 4.1 Fast Reasoning. GPT-5 mini CharXiv value is with python.
- Gemini 2.5 Pro p.5–6
Results as of June 2025, as published in Google's model card. Single-attempt pass@1. Competitor figures are providers' own numbers as listed by Google; Claude 4 Opus is 32K thinking. Aider Polyglot uses diff-fenced for 2.5 Pro and diff for the others. MRCR v2 for Claude 4 Opus is with no thinking.
- Gemini 2.5 Flash-Lite p.5
Results for the 06-17 release (the stable model) as of June 2025, as published in Google's model card. Results for the shut-down 09-2025 preview are left out.
Only each model's own maker's number is shown; scores a maker reports for rival models are left out.