CrossModel
Back to model catalog

Compare models

Context, limits, capabilities, price and use cases side by side — up to 4 models at a time. The URL holds your selection, so you can share it.

GPT-6 AstraGPT-5.6 TerraGPT-5.6 SolChat with these 3
AttributeGPT-6 Astraopenai/gpt-6-astraGPT-5.6 Terraopenai/gpt-5.6-terraGPT-5.6 Solopenai/gpt-5.6-solPromo price
Specs
Context window1M1M1M
Max output128K128K128K
Input modalitiesTextImageTextImageTextImage
Output modalitiesTextTextText
Capabilities
StreamingSupportedSupportedSupported
Tool callingSupportedSupportedSupported
Structured output (JSON)SupportedSupportedSupported
Image inputSupportedSupportedSupported
Thinking modeSupportedSupportedSupported
Price / 1M tokens
Input$ 10.00>= 272K$ 20.00$ 2.00>= 272K$ 4.00$ 5.00$ 4.00>= 272K$ 10.00$ 8.00
Output$ 50.00>= 272K$ 75.00$ 12.00>= 272K$ 18.00$ 30.00$ 20.00>= 272K$ 45.00$ 30.00
Cache read$ 1.00>= 272K$ 2.00$ 0.20>= 272K$ 0.40$ 0.50$ 0.40>= 272K$ 1.00$ 0.80
Cache write$ 12.50>= 272K$ 25.00$ 2.50>= 272K$ 5.00$ 6.25$ 5.00>= 272K$ 12.50$ 10.00
What it is good at
Best for
  • Software engineering
  • Professional deliverables
  • Research with computer use
  • Scientific reasoning
  • Everyday knowledge work
  • Cost-aware agentic coding
  • Frontier agentic coding
  • Complex professional work
Published benchmarks
Terminal-Bench 2.1pass_rate—
  • 87.4%effort max(setup not fully disclosed)
  • 88.8%effort max(setup not fully disclosed)
Terminal-Bench 4.0pass_rate
  • 57.9%(setup not fully disclosed)
——
BrowseComp (with tools)accuracysetups differ by: reasoning
  • 91.5%(setup not fully disclosed)
  • 87.5%effort max(setup not fully disclosed)
  • 90.4%effort max(setup not fully disclosed)
Agents' Last Examscoresetups differ by: reasoning
  • 59.3%(setup not fully disclosed)
  • 50.4%effort max(setup not fully disclosed)
  • 52.7%effort max(setup not fully disclosed)
DeepSWE 1.1resolved_rate
  • 74.1%(setup not fully disclosed)
——
SWE-Bench Pro (Public)pass_rate—
  • 63.4%effort max(setup not fully disclosed)
  • 64.6%effort max(setup not fully disclosed)
OSWorld 2.0success_rate—
  • 50.2%effort max(setup not fully disclosed)
  • 62.6%effort max(setup not fully disclosed)
OSWorld 2.0 (v2026.08.08 offline, partial score)score
  • 72.6%(setup not fully disclosed)
——
OpenAI MRCR v2 8-needle 512K–1Maccuracysetups differ by: reasoning
  • 96.3%(setup not fully disclosed)
  • 72.5%effort max(setup not fully disclosed)
  • 73.8%effort max(setup not fully disclosed)
FrontierMath Tier 4 (v2)score
  • 97.6%(setup not fully disclosed)
——
MMMU Pro (with tools)accuracy—
  • 82%effort max(setup not fully disclosed)
  • 84.6%effort max(setup not fully disclosed)
GPQA Diamondaccuracysetups differ by: reasoning
  • 96%(setup not fully disclosed)
  • 92.9%effort max(setup not fully disclosed)
  • 94.6%effort max(setup not fully disclosed)
Toolathlonscore—
  • 53.1%effort max(setup not fully disclosed)
  • 58%effort max(setup not fully disclosed)