Gemini 1.5 Pro
Gemini 1.5 ProCompare inon
Benchmarks of Gemini 1.5 Pro13
BenchmarkByScoreRank
Reasoning2
Multimodal3
Writing4
Health & law1
Documents1Leads on 1
Legacy · saturated or no longer reported2
No benchmark matches
—per task?
price not verifiedprice
—output speed?
—context
Rankingconfiguration unstated?
Retired models are left out of the current rankings.
Alternatives?
ModelScoreCostPer taskWhat changes
BetterGPT-5.6 Lunalow+2.8—$0.01
OpenGLM 5.3 Flashmax+66.8—$0.28Defaults to max · Self-hosted+4BetterGPT-6 Lunamedium+19.2—$0.017Function calling only with none · Chat Completions+3
BetterClaude Haiku 5.5low+7.9—$0.024Remove sampling parameters+5BetterGPT-6.1 Sollow+77.8—$0.13Remove unsupported parameters+5ModelScoreCostPer taskWhat changes
Nothing here yet.
ModelScoreCostPer taskWhat changes
GPT-5.6 Lunalow+2.8—$0.01GPT-6 Lunamedium+19.2—$0.017Function calling only with none · Chat Completions+3Claude Haiku 5.5low+7.9—$0.024Remove sampling parameters+5GPT-6.1 Sollow+77.8—$0.13Remove unsupported parameters+5GPT-6 Sollow+25.6—$0.13ModelScoreCostPer taskWhat changes
GLM 5.3 FlashmaxOpen+66.8—$0.28Defaults to max · Self-hosted+4
DeepSeek V4 Pro 0813highOpen+63.6—$1.32 / $3.96Pass back reasoning_content · Chat Completions+4
Kimi K3maxOpen+61.7—$2.00Sampling parameters are fixed+3TInkling SmallxhighOpen+39.3—$0.45 / $1.20
Qwen3.8 27BxhighOpen+38.8—$1.01max_tokens range · QwenCloud+4ModelScoreCostPer taskWhat changes
Gemini 4 Argonhigh+97.1—*$1.99Synchronous output stops at 65,536+2Gemini 3.1 Pro Previewunstated+88.1—$2 / $12Cannot use both thinking controlsGemini 3.8 Flashmedium+87.5—*$0.93Sampling parameters are ignored+1Gemini 3.6 Flashhigh+65.3—*$1.60Gemini 3 Flash Previewhigh+34—$0.50 / $3Gemini 3.5 Flash Litehigh+7.9—$0.19Gemini 2.5 Prothinking+5.1—$1.25 / $10Gemini Robotics ER 2 Previewn/a——All Google models →Benchmarks
all categoriesChat & Knowledge
Arena Text · overall1,351
Vals LegalBench69.1
MMLU-Pro · official boardlab69
Writing & Language
Arena Text · creative writing · Gemini 1.5 Flash (001) / Gemini 1.5 Pro (001) / Mistral Large 24021,323
Vision & Documents
Arena Vision · overall1,161.4
LVBenchlab33.1
VideoMMMUlab53.9
Video-MME 1 · without subtitles/audio75
Video-MME 1 · with subtitles/audio81.3
FAQ
How much does Gemini 1.5 Pro cost?›
There is no per-unit API price: price not verified.
What is Gemini 1.5 Pro?›
Gemini 1.5 Pro is a language model from Google.
What are the best alternatives to Gemini 1.5 Pro?›
GPT-5.6 Luna (better), GLM 5.3 Flash (open weights).