Claude 4 released
Anthropic · Model release
Source confirmed
Data as of October 14, 2026 · How the score is built
EstablishedProprietaryReasoning
Released May 22, 2025200K contextClaude Opus 4 and Claude Sonnet 4 system card
Claude 4 Opus Thinking
Decision readingClaude 4 Opus Thinking is tracked, but not publicly ranked yet. The profile exposes 4 sourced benchmark rows and leaves unsupported fields blank until a published record exists.
Released May 22, 2025 — see all recent releases
Claude 4 Opus Thinking will be repriced, updated or retired. Get each notice with its source and date. Follow model changes
Decision snapshot
Each value carries a field reference instead of floating alone. Markers compare this model with the current ranked and priced catalog; they are not absolute quality thresholds.
Capability
Unranked
field median 49.8Not eligible for a public rank
Price
Not listed
input median $0.80No comparable first-party hosted token rate
Speed
Not measured
field median 90 tok/sTime to first token not measured
Context
200Ktokens
field median 256,000Reported for this model; direct source link not stored
Strongest published evidence
Published rows are visible, but no category has enough eligible evidence for a comparative rank.
Validate before choosing
4 published rows leave some tracked benchmark slots empty. No comparable first-party API token rate is published.
Source-linked · 4 displayable benchmark rows
Follow model changesCategory score record
Scores and ranks appear only where published evidence can be displayed. The table keeps the score, weight, cohort, and evidence state together.
| Category | Score | Rank | Percentile | Weight | Benchmarks | Evidence |
|---|---|---|---|---|---|---|
| AgenticWeight 22%0 benchmarksNot measured | Not measured | 0 benchmarks | Not measured | |||
| CodingWeight 20%0 benchmarksNot measured | Not measured | 0 benchmarks | Not measured | |||
| ReasoningWeight 17%0 benchmarksNot measured | Not measured | 0 benchmarks | Not measured | |||
| MultimodalWeight 12%1 benchmarkVerified | Score pending | 1 benchmark | Verified | |||
| KnowledgeRank Not rankedWeight 12%2 benchmarksVerified | 70.6 | 2 benchmarks | Verified | |||
| MultilingualWeight 7%0 benchmarksNot measured | Not measured | 0 benchmarks | Not measured | |||
| Inst. FollowingWeight 5%0 benchmarksNot measured | Not measured | 0 benchmarks | Not measured | |||
| MathWeight 5%1 benchmarkVerified | Score pending | 1 benchmark | Verified |
4 of 670 tracked benchmark slots have displayable evidence · bars run 0–100
Coverage detailsHow much of this is verified
Coverage is split by category so a strong number never hides a thin evidence base. Verified means the row is tied to a published source; provisional rows remain visible but separate.
- AgenticNot measured
- CodingNot measured
- ReasoningNot measured
- Multimodal1/1 verified
- Knowledge2/2 verified
- MultilingualNot measured
- Inst. FollowingNot measured
- Math1/1 verified
Verified sourceProvisionalNot measured
Benchmark ledger
Multimodal opens by default. The marker compares each value with the best source-verified result in the catalog; provisional leaders do not set the reference. Expand the remaining categories for every published row.
Multimodal1 row
| Benchmark | Score | Versus best verified row | Gap | Weight | Evidence |
|---|---|---|---|---|---|
| MMMUMassive Multi-discipline Multimodal Understanding | Score76.5% | Versus best verified row Best verified: Qwen3.5 397B · 85.0% | Gap8.5 behind | WeightDisplay only | Provider exact |
Knowledge2 rows
| Benchmark | Score | Versus best verified row | Gap | Weight | Evidence |
|---|---|---|---|---|---|
| GPQAGraduate-Level Google-Proof Q&A | Score79.6% | Versus best verified row Best verified: GPT-6 Astra · 96% | Gap16.4 behind | Weight3% ref. weight | Provider exact |
| MMMLU | Score88.8% | Versus best verified row Best verified: Interfaze Beta · 90.9% | Gap2.1 behind | WeightDisplay only | Provider exact |
Math1 row
| Benchmark | Score | Versus best verified row | Gap | Weight | Evidence |
|---|---|---|---|---|---|
| AIME 2025American Invitational Mathematics Examination 2025 | Score75.5% | Versus best verified row Best verified: GPT-5.2 · 100% | Gap24.5 behind | WeightDisplay only | Provider exact |
Bars run 0–100; the dark tick marks the best source-verified value
All 4 rowsLineage
The sequence follows explicit supersedes links. Each score is estimated for that model; a relative can inform a sparse estimate but never sets a floor, so a newer release can score below an earlier one. Scores and prices remain blank when the corresponding public row or first-party rate is unavailable.
Radar
Full release historyClaude 4 Opus Thinking release history
Radar confirmed these at the source. Use Claude 4 Opus Thinking in your work? Explore Radar to follow supported changes and choose your alerts.
Radar
Spec sheet
Each documented value carries its source. Missing fields stay visible as not sourced or not published, rather than disappearing from the page.
- API model ID
- Not published
- Context window
- 200K
- Maximum output
- Not sourced yet
- Knowledge cutoff
- Not sourced yet
- Input modalities
- Not sourced yet
- Output modalities
- Not sourced yet
- Parameters
- Not disclosed by the provider
- Availability
- Not sourced yet
- Cloud regions
- Not tracked yet
- Lifecycle
- Established
- API capabilities
- Tool calling, structured outputs, and batch support are not tracked yet
- Prompt caching
- Not documented in the pricing record
- Self-host
- Weights are not published
- Rate limits
- Not tracked yet
How to read this profile
The visual layer above carries the decisions. These notes preserve the model, ranking, coverage, and family context behind the numbers.
We track Claude 4 Opus Thinking, but the public leaderboard excludes this profile until enough non-generated benchmark coverage is available. Only published rows appear above.
Claude 4 Opus Thinking is a proprietary model with a 200K context window. It uses an explicit reasoning mode, which can improve complex problem solving while adding latency and token use.
Official exact values from Anthropic's May 22, 2025 launch table, extended thinking up to 64K tokens, without parallel test-time compute. BenchLM stores gpqa, mmmlu, aime2025, mmmu. Each value's source and evaluation setting is recorded in row-level source verification. Kept out of rankings because the published results cover few of the benchmarks BenchLM ranks on.
Claude 4 Opus Thinking sits in the Claude 4 Opus family with Claude 4 Opus. 4 of 670 tracked benchmark slots currently have displayable evidence. Missing categories stay blank.
Last updated October 14, 2026. Runtime fields remain blank until a sourced snapshot exists.
Questions
How does Claude 4 Opus Thinking perform overall in AI benchmarks?
Claude 4 Opus Thinking has 4 source-displayable benchmark rows, but it does not qualify for a public overall rank. The available rows remain visible by category without being converted into a site-wide score. Missing evidence stays blank instead of being estimated from an earlier model.
Is Claude 4 Opus Thinking good for knowledge and understanding?
Claude 4 Opus Thinking has source-displayable benchmark coverage for knowledge and understanding, but the public category table does not assign it a rank there. The individual rows remain available for inspection. A missing category position means the evidence threshold was not met; it does not convert the model's unmeasured work into a zero.
Is Claude 4 Opus Thinking good for mathematics?
Claude 4 Opus Thinking has source-displayable benchmark coverage for mathematics, but the public category table does not assign it a rank there. The individual rows remain available for inspection. A missing category position means the evidence threshold was not met; it does not convert the model's unmeasured work into a zero.
Is Claude 4 Opus Thinking good for multimodal and grounded tasks?
Claude 4 Opus Thinking has source-displayable benchmark coverage for multimodal and grounded tasks, but the public category table does not assign it a rank there. The individual rows remain available for inspection. A missing category position means the evidence threshold was not met; it does not convert the model's unmeasured work into a zero.
Which sibling models are related to Claude 4 Opus Thinking?
Claude 4 Opus Thinking belongs to the Claude 4 Opus family. Related tracked variants include Claude 4 Opus. A sibling link indicates shared lineage or a documented configuration relationship; it does not mean the variants have identical pricing, context limits, benchmark evidence, or deployment behavior. Compare before switching.
Does Claude 4 Opus Thinking have full benchmark coverage on BenchLM?
No. Claude 4 Opus Thinking currently has 4 source-displayable rows across 670 tracked benchmark slots. The profile exposes published, non-generated evidence and leaves missing categories blank until an exact evaluation is available. Coverage describes how much was measured; it is not a penalty added to an individual benchmark result.
What is the context window size of Claude 4 Opus Thinking?
Claude 4 Opus Thinking has a reported context window of 200K in the exact-model catalog record. The value stays visible, but the profile marks its source link as unavailable instead of presenting it as directly documented. Maximum output length remains separate because providers often publish a different limit.