Decision support

Gemini Omni 1.2 Flash vs MiniMax H3

Compare canonical objects directly. The useful dimensions change with the object type, so model and hardware comparisons stay separate.

Gemini Omni 1.2 Flash

Google DeepMind

Sources:OpenRouter

MiniMax H3

MiniMax

Sources:models.dev

Benchmark results

Head to head on 3 benchmarks both models report · 2 ties

  • Gemini Omni 1.2 Flash1lead
  • MiniMax H30leads
  • Arena Text to Video

    Arena rating · Higher is better

    • Gemini Omni 1.2 Flash
      Best1540
      +84 ahead · Arena #1CI 1524 to 1556
    • MiniMax H3
      1456
      Arena #11CI 1448 to 1464
    Runs and sources
    Gemini Omni 1.2 Flash
    • default154095% CI 1524 to 1556 · 1,714 votes
    MiniMax H3
    • default145695% CI 1448 to 1464 · 29,257 votes
  • Arena Image to Video

    Arena rating · Higher is better

    Tie, within 95% CI
    • Gemini Omni 1.2 Flash
      1503
      Arena #1CI 1491 to 1515
    • MiniMax H3
      1493
      Arena #3CI 1488 to 1499
    Runs and sources
    Gemini Omni 1.2 Flash
    • default150395% CI 1491 to 1515 · 2,666 votes
    MiniMax H3
    • default149395% CI 1488 to 1499 · 121,481 votes
  • Arena Video Edit

    Arena rating · Higher is better

    Tie, within 95% CI
    • Gemini Omni 1.2 Flash
      1396
      Arena #3CI 1379 to 1412
    • MiniMax H3
      1378
      Arena #5CI 1369 to 1388
    Runs and sources
    Gemini Omni 1.2 Flash
    • default139695% CI 1379 to 1412 · 1,167 votes
    MiniMax H3
    • default137895% CI 1369 to 1388 · 8,385 votes

Each model's best published result is shown; "Not reported" means no matched evaluation, not a score of zero. Arena and DeepSWE ranks are the leaderboards' own; other ranks are among catalogue models with a score. Results from different harnesses or settings are not directly comparable.

Arena ratings: Arena (lmarena-ai/leaderboard-dataset), licensed CC BY 4.0. Ratings come from pairwise human votes and are only comparable within one leaderboard; the interval is Arena's 95% confidence interval. Model names are matched to the Vertical Tabs catalog.

Model specifications

Release date
November 5, 2026
July 31, 2026
Context window
131K
—
Native context
—
—
Max output tokens
65,536
—
Knowledge cutoff
—
—
Open weights
Closed
Open weights
Parameter count
—
33.1B

API pricing · USD per 1M tokens

Input
$1.50
—
Output
$9.00
—
Cached input
—
—
Cache write
—
—

Capabilities and modalities

Input modalities
text, image, video
text, image, video, audio
Output modalities
text, video
video, audio
Tool calling
—
—
Reasoning option
Supported
—
Supported options
include_reasoning, max_tokens, reasoning, reasoning_effort, seed, temperature, top_p
—
Capabilities
—
—

Architecture and availability

Architecture
—
—
Model families
—
—
Tokenizer
Gemini
—
Instruction format
—
—
License
—
MiniMax H3 Community License Agreement
Providers
1
0
Provider endpoints
1
0
Ollama variants
0
0
Metadata source
ai-research
models.dev

A dash means the field is not reported. Provider-specific performance and pricing may differ.

To give you the best experience, we use cookies for personalization, insights, and performance. Learn more.