Intelligence Index
AA · Chat / text · Combined
It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.
Rank #22 · Source label: Claude Opus 5 (High)
verified runtimeexact alias
Raw row drilldownsource row, percentile, last updated, eligibility
- Source
- Artificial Analysis
- Raw value
- 48
- Percentile
- 96.2%
- Last updated
- recent
- Eligibility
- headline eligible
Parsed from Artificial Analysis public leaderboard field `intelligenceIndex`.
96.2% percentile inside its fair comparison set48Raw benchmark value
AA-Omniscience accuracy
AA · Chat / text · Objective
It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.
Rank #23 · Source label: Claude Opus 5 (High)
verified runtimeexact alias
Raw row drilldownsource row, percentile, last updated, eligibility
- Source
- Artificial Analysis
- Raw value
- 58.9%
- Percentile
- 95.2%
- Last updated
- recent
- Eligibility
- headline eligible
Parsed from Artificial Analysis public leaderboard field `omniscienceAccuracy`.
95.2% percentile inside its fair comparison set58.9%Raw benchmark value
AA-Omniscience non-hallucination
AA · Chat / text · Objective
It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.
Rank #132 · Source label: Claude Opus 5 (High)
verified runtimeexact alias
Raw row drilldownsource row, percentile, last updated, eligibility
- Source
- Artificial Analysis
- Raw value
- 38.8%
- Percentile
- 71.2%
- Last updated
- recent
- Eligibility
- headline eligible
Parsed from Artificial Analysis public leaderboard field `omniscienceNonHallucination`.
71.2% percentile inside its fair comparison set38.8%Raw benchmark value
Input price
AA · Chat / text · Speed / cost
It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.
Rank #332 · Source label: Claude Opus 5 (High)
verified runtimeexact alias
Raw row drilldownsource row, percentile, last updated, eligibility
- Source
- Artificial Analysis
- Raw value
- $5 /1M input tokens
- Percentile
- 9.2%
- Last updated
- recent
- Eligibility
- headline eligible
Parsed from Artificial Analysis public leaderboard field `price1mInputTokens`.
9.2% percentile inside its fair comparison set$5 /1M input tokensRaw benchmark value
Output price
AA · Chat / text · Speed / cost
It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.
Rank #331 · Source label: Claude Opus 5 (High)
verified runtimeexact alias
Raw row drilldownsource row, percentile, last updated, eligibility
- Source
- Artificial Analysis
- Raw value
- $25 /1M output tokens
- Percentile
- 9%
- Last updated
- recent
- Eligibility
- headline eligible
Parsed from Artificial Analysis public leaderboard field `price1mOutputTokens`.
9% percentile inside its fair comparison set$25 /1M output tokensRaw benchmark value
Output Speed
AA · Chat / text · Speed / cost
It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.
Rank #209 · Source label: Claude Opus 5 (High)
verified runtimeexact alias
Raw row drilldownsource row, percentile, last updated, eligibility
- Source
- Artificial Analysis
- Raw value
- 56.2 tokens/s
- Percentile
- 22.1%
- Last updated
- recent
- Eligibility
- headline eligible
Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.
22.1% percentile inside its fair comparison set56.2 tokens/sRaw benchmark value
Time to first token
AA · Chat / text · Speed / cost
It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.
Rank #216 · Source label: Claude Opus 5 (High)
verified runtimeexact alias
Raw row drilldownsource row, percentile, last updated, eligibility
- Source
- Artificial Analysis
- Raw value
- 22.25s
- Percentile
- 20.1%
- Last updated
- recent
- Eligibility
- headline eligible
Parsed from Artificial Analysis public leaderboard field `medianTimeToFirstTokenSeconds`.
20.1% percentile inside its fair comparison set22.25sRaw benchmark value
Time to first answer token
AA · Chat / text · Speed / cost
It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.
Rank #150 · Source label: Claude Opus 5 (High)
verified runtimeexact alias
Raw row drilldownsource row, percentile, last updated, eligibility
- Source
- Artificial Analysis
- Raw value
- 22.25s
- Percentile
- 44.2%
- Last updated
- recent
- Eligibility
- headline eligible
Parsed from Artificial Analysis public leaderboard field `medianTimeToFirstAnswerTokenSeconds`.
44.2% percentile inside its fair comparison set22.25sRaw benchmark value
Text Arena
AR · Chat / text · Human
It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.
Rank #13
verified runtimeexact alias
Raw row drilldownsource row, percentile, last updated, eligibility
- Source
- Arena
- Raw value
- 1,490
- Percentile
- 96.8%
- Last updated
- aging
- Eligibility
- headline eligible
Parsed from Arena leaderboard dataset row `claude-opus-5-high`. Category: overall. Source rank: #13. Votes: 59482. Organization: anthropic. License: Proprietary.
96.8% percentile inside its fair comparison set1,490Raw benchmark valueCI 1,486 - 1,494
Text Arena · Creative Writing
AR · Chat / text · Human
It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.
Rank #13
verified runtimeexact alias
Raw row drilldownsource row, percentile, last updated, eligibility
- Source
- Arena
- Raw value
- 1,471
- Percentile
- 96.8%
- Last updated
- aging
- Eligibility
- headline eligible
Parsed from Arena leaderboard dataset row `claude-opus-5-high`. Category: creative_writing. Source rank: #13. Votes: 13263. Organization: anthropic. License: Proprietary.
96.8% percentile inside its fair comparison set1,471Raw benchmark valueCI 1,465 - 1,478
Text Arena · English
AR · Chat / text · Human
It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.
Rank #16
verified runtimeexact alias
Raw row drilldownsource row, percentile, last updated, eligibility
- Source
- Arena
- Raw value
- 1,493
- Percentile
- 96%
- Last updated
- aging
- Eligibility
- headline eligible
Parsed from Arena leaderboard dataset row `claude-opus-5-high`. Category: english. Source rank: #16. Votes: 24266. Organization: anthropic. License: Proprietary.
96% percentile inside its fair comparison set1,493Raw benchmark valueCI 1,488 - 1,498
Text Arena · Exclude Ties
AR · Chat / text · Human
It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.
Rank #13
verified runtimeexact alias
Raw row drilldownsource row, percentile, last updated, eligibility
- Source
- Arena
- Raw value
- 1,504
- Percentile
- 96.8%
- Last updated
- aging
- Eligibility
- headline eligible
Parsed from Arena leaderboard dataset row `claude-opus-5-high`. Category: exclude_ties. Source rank: #13. Votes: 44941. Organization: anthropic. License: Proprietary.
96.8% percentile inside its fair comparison set1,504Raw benchmark valueCI 1,499 - 1,509
Text Arena · Hard Prompts
AR · Chat / text · Human
It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.
Rank #12
verified runtimeexact alias
Raw row drilldownsource row, percentile, last updated, eligibility
- Source
- Arena
- Raw value
- 1,515
- Percentile
- 97.1%
- Last updated
- aging
- Eligibility
- headline eligible
Parsed from Arena leaderboard dataset row `claude-opus-5-high`. Category: hard_prompts. Source rank: #12. Votes: 39034. Organization: anthropic. License: Proprietary.
97.1% percentile inside its fair comparison set1,515Raw benchmark valueCI 1,511 - 1,520
Text Arena · Hard Prompts English
AR · Chat / text · Human
It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.
Rank #13
verified runtimeexact alias
Raw row drilldownsource row, percentile, last updated, eligibility
- Source
- Arena
- Raw value
- 1,515
- Percentile
- 96.8%
- Last updated
- aging
- Eligibility
- headline eligible
Parsed from Arena leaderboard dataset row `claude-opus-5-high`. Category: hard_prompts_english. Source rank: #13. Votes: 15730. Organization: anthropic. License: Proprietary.
96.8% percentile inside its fair comparison set1,515Raw benchmark valueCI 1,508 - 1,521
Text Arena · Instruction Following
AR · Chat / text · Human
It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.
Rank #8
verified runtimeexact alias
Raw row drilldownsource row, percentile, last updated, eligibility
- Source
- Arena
- Raw value
- 1,496
- Percentile
- 98.1%
- Last updated
- aging
- Eligibility
- headline eligible
Parsed from Arena leaderboard dataset row `claude-opus-5-high`. Category: instruction_following. Source rank: #8. Votes: 21069. Organization: anthropic. License: Proprietary.
98.1% percentile inside its fair comparison set1,496Raw benchmark valueCI 1,490 - 1,502
Text Arena · Longer Query
AR · Chat / text · Human
It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.
Rank #10
verified runtimeexact alias
Raw row drilldownsource row, percentile, last updated, eligibility
- Source
- Arena
- Raw value
- 1,504
- Percentile
- 97.5%
- Last updated
- aging
- Eligibility
- headline eligible
Parsed from Arena leaderboard dataset row `claude-opus-5-high`. Category: longer_query. Source rank: #10. Votes: 28188. Organization: anthropic. License: Proprietary.
97.5% percentile inside its fair comparison set1,504Raw benchmark valueCI 1,498 - 1,509
Text Arena · Multi Turn
AR · Chat / text · Human
It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.
Rank #31
verified runtimeexact alias
Raw row drilldownsource row, percentile, last updated, eligibility
- Source
- Arena
- Raw value
- 1,484
- Percentile
- 92%
- Last updated
- aging
- Eligibility
- headline eligible
Parsed from Arena leaderboard dataset row `claude-opus-5-high`. Category: multi_turn. Source rank: #32. Votes: 9304. Organization: anthropic. License: Proprietary.
92% percentile inside its fair comparison set1,484Raw benchmark valueCI 1,476 - 1,491
Text Arena · No Style Control
AR · Chat / text · Human
It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.
Rank #6
verified runtimeexact alias
Raw row drilldownsource row, percentile, last updated, eligibility
- Source
- Arena
- Raw value
- 1,502
- Percentile
- 98.7%
- Last updated
- aging
- Eligibility
- headline eligible
Parsed from Arena leaderboard dataset row `claude-opus-5-high`. Category: overall. Source rank: #6. Votes: 59482. Organization: anthropic. License: Proprietary.
98.7% percentile inside its fair comparison set1,502Raw benchmark valueCI 1,498 - 1,506
Text Arena · Creative Writing · No Style Control
AR · Chat / text · Human
It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.
Rank #10
verified runtimeexact alias
Raw row drilldownsource row, percentile, last updated, eligibility
- Source
- Arena
- Raw value
- 1,486
- Percentile
- 97.6%
- Last updated
- aging
- Eligibility
- headline eligible
Parsed from Arena leaderboard dataset row `claude-opus-5-high`. Category: creative_writing. Source rank: #10. Votes: 13263. Organization: anthropic. License: Proprietary.
97.6% percentile inside its fair comparison set1,486Raw benchmark valueCI 1,479 - 1,493
Text Arena · English · No Style Control
AR · Chat / text · Human
It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.
Rank #8
verified runtimeexact alias
Raw row drilldownsource row, percentile, last updated, eligibility
- Source
- Arena
- Raw value
- 1,502
- Percentile
- 98.1%
- Last updated
- aging
- Eligibility
- headline eligible
Parsed from Arena leaderboard dataset row `claude-opus-5-high`. Category: english. Source rank: #8. Votes: 24266. Organization: anthropic. License: Proprietary.
98.1% percentile inside its fair comparison set1,502Raw benchmark valueCI 1,496 - 1,507
Text Arena · Exclude Ties · No Style Control
AR · Chat / text · Human
It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.
Rank #6
verified runtimeexact alias
Raw row drilldownsource row, percentile, last updated, eligibility
- Source
- Arena
- Raw value
- 1,518
- Percentile
- 98.7%
- Last updated
- aging
- Eligibility
- headline eligible
Parsed from Arena leaderboard dataset row `claude-opus-5-high`. Category: exclude_ties. Source rank: #6. Votes: 44941. Organization: anthropic. License: Proprietary.
98.7% percentile inside its fair comparison set1,518Raw benchmark valueCI 1,513 - 1,523
Text Arena · Hard Prompts · No Style Control
AR · Chat / text · Human
It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.
Rank #7
verified runtimeexact alias
Raw row drilldownsource row, percentile, last updated, eligibility
- Source
- Arena
- Raw value
- 1,522
- Percentile
- 98.4%
- Last updated
- aging
- Eligibility
- headline eligible
Parsed from Arena leaderboard dataset row `claude-opus-5-high`. Category: hard_prompts. Source rank: #7. Votes: 39034. Organization: anthropic. License: Proprietary.
98.4% percentile inside its fair comparison set1,522Raw benchmark valueCI 1,517 - 1,527
Text Arena · Hard Prompts English · No Style Control
AR · Chat / text · Human
It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.
Rank #8
verified runtimeexact alias
Raw row drilldownsource row, percentile, last updated, eligibility
- Source
- Arena
- Raw value
- 1,519
- Percentile
- 98.1%
- Last updated
- aging
- Eligibility
- headline eligible
Parsed from Arena leaderboard dataset row `claude-opus-5-high`. Category: hard_prompts_english. Source rank: #8. Votes: 15730. Organization: anthropic. License: Proprietary.
98.1% percentile inside its fair comparison set1,519Raw benchmark valueCI 1,513 - 1,526
Text Arena · Instruction Following · No Style Control
AR · Chat / text · Human
It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.
Rank #6
verified runtimeexact alias
Raw row drilldownsource row, percentile, last updated, eligibility
- Source
- Arena
- Raw value
- 1,515
- Percentile
- 98.7%
- Last updated
- aging
- Eligibility
- headline eligible
Parsed from Arena leaderboard dataset row `claude-opus-5-high`. Category: instruction_following. Source rank: #6. Votes: 21069. Organization: anthropic. License: Proprietary.
98.7% percentile inside its fair comparison set1,515Raw benchmark valueCI 1,509 - 1,520
Text Arena · Longer Query · No Style Control
AR · Chat / text · Human
It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.
Rank #7
verified runtimeexact alias
Raw row drilldownsource row, percentile, last updated, eligibility
- Source
- Arena
- Raw value
- 1,514
- Percentile
- 98.3%
- Last updated
- aging
- Eligibility
- headline eligible
Parsed from Arena leaderboard dataset row `claude-opus-5-high`. Category: longer_query. Source rank: #7. Votes: 28188. Organization: anthropic. License: Proprietary.
98.3% percentile inside its fair comparison set1,514Raw benchmark valueCI 1,508 - 1,519
Text Arena · Multi Turn · No Style Control
AR · Chat / text · Human
It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.
Rank #12
verified runtimeexact alias
Raw row drilldownsource row, percentile, last updated, eligibility
- Source
- Arena
- Raw value
- 1,492
- Percentile
- 97.1%
- Last updated
- aging
- Eligibility
- headline eligible
Parsed from Arena leaderboard dataset row `claude-opus-5-high`. Category: multi_turn. Source rank: #12. Votes: 9304. Organization: anthropic. License: Proprietary.
97.1% percentile inside its fair comparison set1,492Raw benchmark valueCI 1,484 - 1,499