Long Context

Composite performance across 2 benchmarks · Normalized 0–100 · At least 2 scores required · Ranked by average performance

#	Model	Provider	AA Long Con...	BFCL Multi-...	Avg	Coverage	Price	Value
1	grok-4-1-fast-reasoning	SpaceXAI	74.0%	62.5%	82.9	2/2	—	—
2	Grok 4	SpaceXAI	68.0%	50.5%	71.6	2/2	$18.00/M	4.0
3	Grok 4.1 Fast (Non-reasoning)	SpaceXAI	31.3%	52.0%	51.9	2/2	—	—
4	Cohere: Command A	Cohere	52.7%	25.0%	46.2	2/2	$12.50/M	3.7
5	Microsoft: Phi 4	Microsoft	0.0%	3.0%	2.0	2/2	$0.21/M	9.3
6	Granite 4.0 350M	IBM	0.0%	2.0%	1.3	2/2	—	—

grok-4-1-fast-reasoning leads on raw performance, but Microsoft: Phi 4 delivers 92900% more performance per dollar.

Access this data

JSON GET /api/v1

[
  {
    "rank": 1,
    "model": "grok-4-1-fast-reasoning",
    "provider": "SpaceXAI",
    "avg_score": 82.9,
    "cost": null,
    "cost_unit": "million_tokens",
    "value": null
  },
  {
    "rank": 2,
    "model": "Grok 4",
    "provider": "SpaceXAI",
    "avg_score": 71.6,
    "cost": 18.0,
    "cost_unit": "million_tokens",
    "value": 4.0
  },
  {
    "rank": 3,
    "model": "Grok 4.1 Fast (Non-reasoning)",
    "provider": "SpaceXAI",
    "avg_score": 51.9,
    "cost": null,
    "cost_unit": "million_tokens",
    "value": null
  }
]

Curl

$ curl -s https://rightrank.ai/api/v1/rankings/long-context.json | jq '.[:3]'

CLI brew install rightrank

$ rightrank top long-context --limit 5
$ rightrank compare claude-opus-4.6 gpt-5.4-pro --category long-context
$ rightrank value long-context  # best performance per dollar

Claude Code Skill Skill

# In Claude Code, use the RightRank skill:
/rightrank best model for long-context
/rightrank compare top 5 by value
/rightrank cheapest model scoring above 80 on long-context