# Claude Opus 4.7Extra high

> Source: Benchize (https://benchize.com) — https://benchize.com/models/claude-opus-4-7-xhigh. When citing or reusing this content, credit "Benchize" and link to https://benchize.com/models/claude-opus-4-7-xhigh.

Anthropic

Canonical URL: https://benchize.com/models/claude-opus-4-7-xhigh
Last updated: Thu, 22 Oct 2026 09:10:07 GMT

Reproduction and quotation must name Benchize, link to the canonical HTML URL, and retain individual source citations.

Anthropic

## Benchmarks

| Benchmark | Score | ± | Rank | Cost | Source |  |
| --- | --- | --- | --- | --- | --- | --- |
| [SimpleQA Verified](https://benchize.com/benchmarks/epoch-ai%3Asimpleqa_verified.md) | 51.7% | SE ±1.58 pp | 19 / 40 | — | [epoch ai · SimpleQA Verified](https://epoch.ai/data/benchmark_data.zip#file=simpleqa_verified.csv) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.517 \| score_fraction \| Best score (across scorers) \| Higher is better \| \| `mean_score` \| 0.517 \| score_fraction \| mean_score \| Higher is better \| ### Configuration benchmarkVersion SimpleQA Verified reasoningBudget Not reported Reasoning effort xhigh sourceModelVersion claude-opus-4-7_xhigh ### Reported statistics Uncertainty Standard error: ±1.58 pp standardError 0.015810153729833274 ### Source [Original source](https://epoch.ai/data/benchmark_data.zip#file=simpleqa_verified.csv) Source epoch ai Original model label claude-opus-4-7 Source version SimpleQA Verified Evaluated 2026-08-27T19:27:26.000Z Observed 2026-10-22T03:00:05.281Z Evidence SHA-256 `e2d3fae377f0ddd3d079bcc3971b9b9388a0a950289effe7b521177ea2e988cc` Source locator `/rows/78` |  |  |  |  |  |  |
| [ArXivMath 01/2026](https://benchize.com/benchmarks/matharena%3Aarxiv--january.md) | 52.17% | 95% CI 37.73–66.61% | 14 / 18 | 1.26usd per problem | [matharena · arxiv--january](https://matharena.ai/competition_tables/arxiv--january) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 52.17 \| percent \| competition \| Higher is better \| \| `cost_per_problem` \| 1.26 \| usd_per_problem \| competition \| Lower is better \| ### Configuration competition arxiv--january predicted false Reasoning effort xhigh sourceModelName Claude-Opus-4.7 (xhigh) sourceModelVersion anthropic/opus_47 thinkingEnabled true ### Reported statistics Uncertainty 95% confidence interval: 37.73–66.61% confidenceInterval95 14.44 problems 23 ### Source [Original source](https://matharena.ai/competition_tables/arxiv--january) Source matharena Original model label Claude-Opus-4.7 (xhigh) Source version arxiv--january Observed 2026-10-22T05:30:07.835Z Evidence SHA-256 `e895f6ccd0711bb1a512b580bab39de8f977c57f83bf492527e4fc710315d706` Source locator `/table/rows/18` |  |  |  |  |  |  |
| [FrontierMath (2025-02-28 private)](https://benchize.com/benchmarks/epoch-ai%3Afrontiermath.md) | 43.79% | SE ±2.92 pp | 1 / 18 | — | [epoch ai · FrontierMath-2025-02-28-Private](https://epoch.ai/data/benchmark_data.zip#file=frontiermath.csv) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.4379310344827586 \| score_fraction \| Best score (across scorers) \| Higher is better \| \| `mean_score` \| 0.4379310344827586 \| score_fraction \| mean_score \| Higher is better \| ### Configuration benchmarkVersion FrontierMath-2025-02-28-Private reasoningBudget Not reported Reasoning effort xhigh sourceModelVersion claude-opus-4-7_xhigh ### Reported statistics Uncertainty Standard error: ±2.92 pp standardError 0.02918426387376174 ### Source [Original source](https://epoch.ai/data/benchmark_data.zip#file=frontiermath.csv) Source epoch ai Original model label claude-opus-4-7 Source version FrontierMath-2025-02-28-Private Evaluated 2026-04-17T11:24:50.000Z Observed 2026-10-22T03:00:05.281Z Evidence SHA-256 `f5c92f0f0b9103abb02308fd428c0806e7c21b91e8a14d43edb8af77ce941598` Source locator `/rows/12` |  |  |  |  |  |  |
| [AIME 2026](https://benchize.com/benchmarks/aime-2026.md) | 95.83% | 95% CI 92.25–99.41% | 12 / 21 | 0.27usd per problem | [matharena · aime--aime_2026](https://matharena.ai/competition_tables/aime--aime_2026) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 95.83 \| percent \| competition \| Higher is better \| \| `cost_per_problem` \| 0.27 \| usd_per_problem \| competition \| Lower is better \| ### Configuration competition aime--aime_2026 predicted false Reasoning effort xhigh sourceModelName Claude-Opus-4.7 (xhigh) sourceModelVersion anthropic/opus_47 thinkingEnabled true ### Reported statistics Uncertainty 95% confidence interval: 92.25–99.41% confidenceInterval95 3.58 problems 30 ### Source [Original source](https://matharena.ai/competition_tables/aime--aime_2026) Source matharena Original model label Claude-Opus-4.7 (xhigh) Source version aime--aime_2026 Observed 2026-10-22T05:30:13.366Z Evidence SHA-256 `58b3ac1e0805975eba566c493b8e0165d41eb7ca517218106e112529fb6342de` Source locator `/table/rows/16` |  |  |  |  |  |  |
| [FrontierCode 1.1 extended](https://benchize.com/benchmarks/frontiercode%3Av1_1%3Aextended.md) | 51.41% | — | 80 / 125 | $5.77 | [frontiercode](https://cognition.com/data/frontiercode-leaderboard/data.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.5141 \| score_fraction \| blocking_criteria_adjusted \| Higher is better \| \| `correct` \| 0.5618 \| score_fraction \| raw_rubric \| Higher is better \| \| `cost` \| 5.7683 \| USD \| per_rollout \| Lower is better \| ### Configuration harness claude-code Reasoning effort xhigh sourceVersion v1_1 subset extended ### Reported statistics flaggedRate 0.0027 sampleSize 150 ### Source [Original source](https://cognition.com/data/frontiercode-leaderboard/data.json) Source frontiercode Original model label Claude Opus 4.7 Observed 2026-10-22T05:40:03.220Z Evidence SHA-256 `ff0040778b7bdf69c705ad7474f771fb5e53cfaf5cf8573b3a4614153543d75f` Source locator `/v1_1/data/Claude%20Opus%204.7/xhigh/extended` |  |  |  |  |  |  |
| [FrontierCode 1 extended](https://benchize.com/benchmarks/frontiercode%3Av1%3Aextended.md) | 43.24% | — | 13 / 39 | $4.93 | [frontiercode](https://cognition.com/data/frontiercode-leaderboard/data.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.4324 \| score_fraction \| blocking_criteria_adjusted \| Higher is better \| \| `correct` \| 0.4697 \| score_fraction \| raw_rubric \| Higher is better \| \| `cost` \| 4.928 \| USD \| per_rollout \| Lower is better \| ### Configuration harness claude-code Reasoning effort xhigh sourceVersion v1 subset extended ### Reported statistics flaggedRate Not reported sampleSize 150 ### Source [Original source](https://cognition.com/data/frontiercode-leaderboard/data.json) Source frontiercode Original model label Claude Opus 4.7 Observed 2026-10-22T05:40:03.220Z Evidence SHA-256 `ff0040778b7bdf69c705ad7474f771fb5e53cfaf5cf8573b3a4614153543d75f` Source locator `/v1/data/Claude%20Opus%204.7/xhigh/extended` |  |  |  |  |  |  |
| [Apex](https://benchize.com/benchmarks/matharena%3Aapex--apex_2025.md) | 40.62% | 95% CI 30.8–50.44% | 6 / 31 | 2.1usd per problem | [matharena · apex--apex_2025](https://matharena.ai/competition_tables/apex--apex_2025) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 40.62 \| percent \| competition \| Higher is better \| \| `cost_per_problem` \| 2.10 \| usd_per_problem \| competition \| Lower is better \| ### Configuration competition apex--apex_2025 predicted false Reasoning effort xhigh sourceModelName Claude-Opus-4.7 (xhigh) sourceModelVersion anthropic/opus_47 thinkingEnabled true ### Reported statistics Uncertainty 95% confidence interval: 30.8–50.44% confidenceInterval95 9.82 problems 12 ### Source [Original source](https://matharena.ai/competition_tables/apex--apex_2025) Source matharena Original model label Claude-Opus-4.7 (xhigh) Source version apex--apex_2025 Observed 2026-10-22T05:30:13.849Z Evidence SHA-256 `20b28370d9d7f5a15a19fc9e4226c9857cdb07bc42b32ccec508e687b7b9f3fc` Source locator `/table/rows/6` |  |  |  |  |  |  |
| [FrontierMath Tier 4 (2025-07-01 private)](https://benchize.com/benchmarks/epoch-ai%3Afrontiermath_tier_4.md) | 22.92% | SE ±6.13 pp | 1 / 15 | — | [epoch ai · FrontierMath-Tier-4-2025-07-01-Private](https://epoch.ai/data/benchmark_data.zip#file=frontiermath_tier_4.csv) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.22916666666666666 \| score_fraction \| Best score (across scorers) \| Higher is better \| \| `mean_score` \| 0.22916666666666666 \| score_fraction \| mean_score \| Higher is better \| ### Configuration benchmarkVersion FrontierMath-Tier-4-2025-07-01-Private reasoningBudget Not reported Reasoning effort xhigh sourceModelVersion claude-opus-4-7_xhigh ### Reported statistics Uncertainty Standard error: ±6.13 pp standardError 0.06130657275434798 ### Source [Original source](https://epoch.ai/data/benchmark_data.zip#file=frontiermath_tier_4.csv) Source epoch ai Original model label claude-opus-4-7 Source version FrontierMath-Tier-4-2025-07-01-Private Evaluated 2026-04-17T12:51:00.000Z Observed 2026-10-22T03:00:05.281Z Evidence SHA-256 `c928e5adccd6e0995d50ede183fb99728d6c5be01951434a3077429ffb5802b2` Source locator `/rows/13` |  |  |  |  |  |  |
| [BrokenArXiv 03/2026](https://benchize.com/benchmarks/matharena%3Aarxiv_false--march.md) | 5.8% | 95% CI 1.47–10.13% | 13 / 14 | 2.21usd per problem | [matharena · arxiv_false--march](https://matharena.ai/competition_tables/arxiv_false--march) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 5.80 \| percent \| competition \| Higher is better \| \| `cost_per_problem` \| 2.21 \| usd_per_problem \| competition \| Lower is better \| ### Configuration competition arxiv_false--march predicted false Reasoning effort xhigh sourceModelName Claude-Opus-4.7 (xhigh) sourceModelVersion anthropic/opus_47 thinkingEnabled true ### Reported statistics Uncertainty 95% confidence interval: 1.47–10.13% confidenceInterval95 4.33 problems 56 ### Source [Original source](https://matharena.ai/competition_tables/arxiv_false--march) Source matharena Original model label Claude-Opus-4.7 (xhigh) Source version arxiv_false--march Observed 2026-10-22T05:30:05.839Z Evidence SHA-256 `b2ea8c773acad8b54736938938d6ee37fa533bfc5b985eefc303733bfcb0c6f0` Source locator `/table/rows/14` |  |  |  |  |  |  |
| [Chess Puzzles](https://benchize.com/benchmarks/epoch-ai%3Achess_puzzles.md) | 36% | SE ±4.82 pp | 33 / 64 | — | [epoch ai · Chess Puzzles](https://epoch.ai/data/benchmark_data.zip#file=chess_puzzles.csv) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.36 \| score_fraction \| Best score (across scorers) \| Higher is better \| \| `mean_score` \| 0.36 \| score_fraction \| mean_score \| Higher is better \| ### Configuration benchmarkVersion Chess Puzzles reasoningBudget Not reported Reasoning effort xhigh sourceModelVersion claude-opus-4-7_xhigh ### Reported statistics Uncertainty Standard error: ±4.82 pp standardError 0.04824181513244218 ### Source [Original source](https://epoch.ai/data/benchmark_data.zip#file=chess_puzzles.csv) Source epoch ai Original model label claude-opus-4-7 Source version Chess Puzzles Evaluated 2026-10-13T13:35:58.000Z Observed 2026-10-22T03:00:05.281Z Evidence SHA-256 `a5b99d6d35252907b04e9a802873a9754ecc0248be92a1ebbd2ef0450e4bb015` Source locator `/rows/104` |  |  |  |  |  |  |
| [BrokenArXiv 04/2026](https://benchize.com/benchmarks/matharena%3Aarxiv_false--april.md) | 4.1% | 95% CI 0.58–7.62% | 18 / 18 | 2.39usd per problem | [matharena · arxiv_false--april](https://matharena.ai/competition_tables/arxiv_false--april) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 4.10 \| percent \| competition \| Higher is better \| \| `cost_per_problem` \| 2.39 \| usd_per_problem \| competition \| Lower is better \| ### Configuration competition arxiv_false--april predicted false Reasoning effort xhigh sourceModelName Claude-Opus-4.7 (xhigh) sourceModelVersion anthropic/opus_47 thinkingEnabled true ### Reported statistics Uncertainty 95% confidence interval: 0.58–7.62% confidenceInterval95 3.52 problems 61 ### Source [Original source](https://matharena.ai/competition_tables/arxiv_false--april) Source matharena Original model label Claude-Opus-4.7 (xhigh) Source version arxiv_false--april Observed 2026-10-22T05:30:06.112Z Evidence SHA-256 `e543f14dac0ba9663e8104a87738726c9848b89171a53fdca89b7baa4a892399` Source locator `/table/rows/18` |  |  |  |  |  |  |
| [ArXivMath Overall](https://benchize.com/benchmarks/matharena%3Aoverall--final_answer_comps.md) | 73.56% | 95% CI 70.27–76.85% | 9 / 20 | 1.13usd per problem | [matharena · overall--final_answer_comps](https://matharena.ai/competition_tables/overall--final_answer_comps) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 73.56 \| percent \| competition \| Higher is better \| \| `cost_per_problem` \| 1.13 \| usd_per_problem \| competition \| Lower is better \| ### Configuration competition overall--final_answer_comps predicted false Reasoning effort xhigh sourceModelName Claude-Opus-4.7 (xhigh) sourceModelVersion anthropic/opus_47 thinkingEnabled true ### Reported statistics Uncertainty 95% confidence interval: 70.27–76.85% confidenceInterval95 3.29 problems Not reported ### Source [Original source](https://matharena.ai/competition_tables/overall--final_answer_comps) Source matharena Original model label Claude-Opus-4.7 (xhigh) Source version overall--final_answer_comps Observed 2026-10-22T05:30:11.571Z Evidence SHA-256 `8b08b20c1ac5aec9a829d234469bc39d40b0eb189790d84b7264c2756ffa161e` Source locator `/table/rows/9` |  |  |  |  |  |  |
| [ArXivMath 04/2026](https://benchize.com/benchmarks/matharena%3Aarxiv--april.md) | 57.5% | 95% CI 46.67–68.33% | 10 / 20 | 0.89usd per problem | [matharena · arxiv--april](https://matharena.ai/competition_tables/arxiv--april) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 57.50 \| percent \| competition \| Higher is better \| \| `cost_per_problem` \| 0.89 \| usd_per_problem \| competition \| Lower is better \| ### Configuration competition arxiv--april predicted false Reasoning effort xhigh sourceModelName Claude-Opus-4.7 (xhigh) sourceModelVersion anthropic/opus_47 thinkingEnabled true ### Reported statistics Uncertainty 95% confidence interval: 46.67–68.33% confidenceInterval95 10.83 problems 40 ### Source [Original source](https://matharena.ai/competition_tables/arxiv--april) Source matharena Original model label Claude-Opus-4.7 (xhigh) Source version arxiv--april Observed 2026-10-22T05:30:08.600Z Evidence SHA-256 `5139c835884bfab38f18d23a248814af4680927310bc5cd2a86ea2eab779e0a7` Source locator `/table/rows/10` |  |  |  |  |  |  |
| [AutomationBench](https://benchize.com/benchmarks/zapier%3Aautomationbench.md) | 9.74% | — | 68 / 113 | $1.26 | [zapier](https://framerusercontent.com/sites/4WTSl4BNjd1q9QFEFibC6h/MBpMAlj5k_Qpj1iTRcXO7kAjUP_VB-QuD3gMvxxThCQ.C6QAp2jN.mjs) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 9.74 \| percent \| reported \| Higher is better \| \| `cost` \| 1.26 \| USD \| per_task \| Lower is better \| ### Configuration benchmarkVersion 1.0.6 costFootnote false Fallback policy Not reported Reasoning effort xhigh Model configuration Claude Opus 4.7 (XHigh) thinkingEnabled true ### Reported statistics rank 77 ### Source [Original source](https://framerusercontent.com/sites/4WTSl4BNjd1q9QFEFibC6h/MBpMAlj5k_Qpj1iTRcXO7kAjUP_VB-QuD3gMvxxThCQ.C6QAp2jN.mjs) Source zapier Original model label Claude Opus 4.7 (XHigh) Observed 2026-10-22T08:20:03.209Z Evidence SHA-256 `6f5ef9e0d3799e2bac5ae924407ac89f608f18c17f3ef238887356808b094579` Source locator `/rows/76` |  |  |  |  |  |  |
| [ToneBench Scriptwriting](https://benchize.com/benchmarks/tonebench%3Ascripts.md) | 1,744.4 | Range 1,697.9–1,786.1 | 54 / 126 | — | [tonebench](https://benchmark.towardsai.com/data/leaderboard.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1744.4 \| rating \| reported \| Higher is better \| \| `overall` \| 78.27 \| percent \| reported \| Higher is better \| \| `anti_slop_numbers` \| 68.65 \| source_score \| rubric \| Higher is better \| \| `continuity_emotion` \| 77.98 \| source_score \| rubric \| Higher is better \| \| `cue_quality` \| 73.59 \| source_score \| rubric \| Higher is better \| \| `hook_strength` \| 79.24 \| source_score \| rubric \| Higher is better \| \| `length_adherence` \| 90.64 \| source_score \| rubric \| Higher is better \| \| `slop` \| 81.3 \| source_score \| rubric \| Higher is better \| \| `slop_score` \| 93.94 \| source_score \| rubric \| Higher is better \| \| `substance_accuracy` \| 79.18 \| source_score \| rubric \| Higher is better \| \| `tone_voice` \| 75.88 \| source_score \| rubric \| Higher is better \| \| `writing_quality` \| 75.73 \| source_score \| rubric \| Higher is better \| \| `youtube_best_practices` \| 75.27 \| source_score \| rubric \| Higher is better \| ### Configuration provider claude-code Reasoning effort unknown scoreScope 10_task_current sourceConfiguration claude-opus-4-7 thinkingEnabled true ### Reported statistics Uncertainty Reported interval: 1,697.9–1,786.1 interval [1697.9,1786.1] rank 54 runCount 5 ### Source [Original source](https://benchmark.towardsai.com/data/leaderboard.json) Source tonebench Original model label Claude Opus 4.7 (xhigh) Evaluated 2026-10-08 Observed 2026-10-22T04:40:14.102Z Evidence SHA-256 `4264338337f418d3ded7ace250cad64fe12cacbd4b79a312bfaf0ae9268a01c3` Source locator `/rows/53` |  |  |  |  |  |  |
| [GPQA Diamond](https://benchize.com/benchmarks/gpqa-diamond.md) | 90.15% | SE ±1.85 pp | 29 / 126 | — | [epoch ai · GPQA diamond](https://epoch.ai/data/benchmark_data.zip#file=gpqa_diamond.csv) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.9015151515151515 \| score_fraction \| Best score (across scorers) \| Higher is better \| \| `mean_score` \| 0.9015151515151515 \| score_fraction \| mean_score \| Higher is better \| ### Configuration benchmarkVersion GPQA diamond reasoningBudget Not reported Reasoning effort xhigh sourceModelVersion claude-opus-4-7_xhigh ### Reported statistics Uncertainty Standard error: ±1.85 pp standardError 0.018464275887293338 ### Source [Original source](https://epoch.ai/data/benchmark_data.zip#file=gpqa_diamond.csv) Source epoch ai Original model label claude-opus-4-7 Source version GPQA diamond Evaluated 2026-04-17T16:16:45.000Z Observed 2026-10-22T03:00:05.281Z Evidence SHA-256 `9ef0b938bdd8406b029d595983ee8ad3a80bd9d64b82605b91b5ce39ba650c39` Source locator `/rows/170` |  |  |  |  |  |  |
| [Apex Shortlist](https://benchize.com/benchmarks/matharena%3Aapex--shortlist_2025.md) | 63.83% | 95% CI 56.96–70.7% | 17 / 25 | 1.83usd per problem | [matharena · apex--shortlist_2025](https://matharena.ai/competition_tables/apex--shortlist_2025) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 63.83 \| percent \| competition \| Higher is better \| \| `cost_per_problem` \| 1.83 \| usd_per_problem \| competition \| Lower is better \| ### Configuration competition apex--shortlist_2025 predicted false Reasoning effort xhigh sourceModelName Claude-Opus-4.7 (xhigh) sourceModelVersion anthropic/opus_47 thinkingEnabled true ### Reported statistics Uncertainty 95% confidence interval: 56.96–70.7% confidenceInterval95 6.87 problems 47 ### Source [Original source](https://matharena.ai/competition_tables/apex--shortlist_2025) Source matharena Original model label Claude-Opus-4.7 (xhigh) Source version apex--shortlist_2025 Observed 2026-10-22T05:30:14.141Z Evidence SHA-256 `74513abecacb4d230d741f4d6df425ce878fb450220e88a1a6823524476c2989` Source locator `/table/rows/20` |  |  |  |  |  |  |
| [FrontierCode 1 main](https://benchize.com/benchmarks/frontiercode%3Av1%3Amain.md) | 22.96% | — | 14 / 39 | $5.93 | [frontiercode](https://cognition.com/data/frontiercode-leaderboard/data.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.2296 \| score_fraction \| blocking_criteria_adjusted \| Higher is better \| \| `correct` \| 0.253 \| score_fraction \| raw_rubric \| Higher is better \| \| `cost` \| 5.9308 \| USD \| per_rollout \| Lower is better \| ### Configuration harness claude-code Reasoning effort xhigh sourceVersion v1 subset main ### Reported statistics flaggedRate Not reported sampleSize 100 ### Source [Original source](https://cognition.com/data/frontiercode-leaderboard/data.json) Source frontiercode Original model label Claude Opus 4.7 Observed 2026-10-22T05:40:03.220Z Evidence SHA-256 `ff0040778b7bdf69c705ad7474f771fb5e53cfaf5cf8573b3a4614153543d75f` Source locator `/v1/data/Claude%20Opus%204.7/xhigh/main` |  |  |  |  |  |  |
| [BrokenArXiv 02/2026](https://benchize.com/benchmarks/matharena%3Aarxiv_false--february.md) | 4.03% | 95% CI 0.57–7.49% | 14 / 15 | 2.36usd per problem | [matharena · arxiv_false--february](https://matharena.ai/competition_tables/arxiv_false--february) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 4.03 \| percent \| competition \| Higher is better \| \| `cost_per_problem` \| 2.36 \| usd_per_problem \| competition \| Lower is better \| ### Configuration competition arxiv_false--february predicted false Reasoning effort xhigh sourceModelName Claude-Opus-4.7 (xhigh) sourceModelVersion anthropic/opus_47 thinkingEnabled true ### Reported statistics Uncertainty 95% confidence interval: 0.57–7.49% confidenceInterval95 3.46 problems 31 ### Source [Original source](https://matharena.ai/competition_tables/arxiv_false--february) Source matharena Original model label Claude-Opus-4.7 (xhigh) Source version arxiv_false--february Observed 2026-10-22T05:30:05.567Z Evidence SHA-256 `a6bc6fc18da7dd181ed727da924f9569d3e323c31c1aba9a4d9fa3bff492bee3` Source locator `/table/rows/14` |  |  |  |  |  |  |
| [OTIS Mock AIME 2024–2025](https://benchize.com/benchmarks/epoch-ai%3Aotis_mock_aime_2024_2025.md) | 97.8% | SE ±2.2 pp | 22 / 124 | — | [epoch ai · OTIS Mock AIME 2024-2025](https://epoch.ai/data/benchmark_data.zip#file=otis_mock_aime_2024_2025.csv) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.978 \| score_fraction \| Best score (across scorers) \| Higher is better \| \| `mean_score` \| 0.978 \| score_fraction \| mean_score \| Higher is better \| ### Configuration benchmarkVersion OTIS Mock AIME 2024-2025 reasoningBudget Not reported Reasoning effort xhigh sourceModelVersion claude-opus-4-7_xhigh ### Reported statistics Uncertainty Standard error: ±2.2 pp standardError 0.022 ### Source [Original source](https://epoch.ai/data/benchmark_data.zip#file=otis_mock_aime_2024_2025.csv) Source epoch ai Original model label claude-opus-4-7 Source version OTIS Mock AIME 2024-2025 Evaluated 2026-04-17T18:26:45.000Z Observed 2026-10-22T03:00:05.281Z Evidence SHA-256 `b7c9da8c0587c82f1e0d814ceb496c24308380b997a16203b6e5d39eb07f4f50` Source locator `/rows/178` |  |  |  |  |  |  |
| [FrontierCode 1.1 main](https://benchize.com/benchmarks/frontiercode%3Av1_1%3Amain.md) | 34.91% | — | 92 / 125 | $6.87 | [frontiercode](https://cognition.com/data/frontiercode-leaderboard/data.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.3491 \| score_fraction \| blocking_criteria_adjusted \| Higher is better \| \| `correct` \| 0.3867 \| score_fraction \| raw_rubric \| Higher is better \| \| `cost` \| 6.8688 \| USD \| per_rollout \| Lower is better \| ### Configuration harness claude-code Reasoning effort xhigh sourceVersion v1_1 subset main ### Reported statistics flaggedRate 0.004 sampleSize 100 ### Source [Original source](https://cognition.com/data/frontiercode-leaderboard/data.json) Source frontiercode Original model label Claude Opus 4.7 Observed 2026-10-22T05:40:03.220Z Evidence SHA-256 `ff0040778b7bdf69c705ad7474f771fb5e53cfaf5cf8573b3a4614153543d75f` Source locator `/v1_1/data/Claude%20Opus%204.7/xhigh/main` |  |  |  |  |  |  |
| [ArXivMath 02/2026](https://benchize.com/benchmarks/matharena%3Aarxiv--february.md) | 40.62% | 95% CI 32.11–49.13% | 11 / 20 | 1.48usd per problem | [matharena · arxiv--february](https://matharena.ai/competition_tables/arxiv--february) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 40.62 \| percent \| competition \| Higher is better \| \| `cost_per_problem` \| 1.48 \| usd_per_problem \| competition \| Lower is better \| ### Configuration competition arxiv--february predicted false Reasoning effort xhigh sourceModelName Claude-Opus-4.7 (xhigh) sourceModelVersion anthropic/opus_47 thinkingEnabled true ### Reported statistics Uncertainty 95% confidence interval: 32.11–49.13% confidenceInterval95 8.51 problems 32 ### Source [Original source](https://matharena.ai/competition_tables/arxiv--february) Source matharena Original model label Claude-Opus-4.7 (xhigh) Source version arxiv--february Observed 2026-10-22T05:30:08.096Z Evidence SHA-256 `3bc5b0a1eb91a0bdaa3d0942ebf82327a8664334b225ae3b2dc1d8b4f57efa51` Source locator `/table/rows/13` |  |  |  |  |  |  |
| [HMMT Feb 2026](https://benchize.com/benchmarks/matharena%3Ahmmt--hmmt_feb_2026.md) | 93.94% | 95% CI 89.87–98.01% | 8 / 21 | 0.56usd per problem | [matharena · hmmt--hmmt_feb_2026](https://matharena.ai/competition_tables/hmmt--hmmt_feb_2026) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 93.94 \| percent \| competition \| Higher is better \| \| `cost_per_problem` \| 0.56 \| usd_per_problem \| competition \| Lower is better \| ### Configuration competition hmmt--hmmt_feb_2026 predicted false Reasoning effort xhigh sourceModelName Claude-Opus-4.7 (xhigh) sourceModelVersion anthropic/opus_47 thinkingEnabled true ### Reported statistics Uncertainty 95% confidence interval: 89.87–98.01% confidenceInterval95 4.07 problems 33 ### Source [Original source](https://matharena.ai/competition_tables/hmmt--hmmt_feb_2026) Source matharena Original model label Claude-Opus-4.7 (xhigh) Source version hmmt--hmmt_feb_2026 Observed 2026-10-22T05:30:13.595Z Evidence SHA-256 `0dce922c33a54d29d4a1872a42d74077b491915c80d8433f4b379ea0b78bb979` Source locator `/table/rows/11` |  |  |  |  |  |  |
| [ArXivMath 03/2026](https://benchize.com/benchmarks/matharena%3Aarxiv--march.md) | 50.83% | 95% CI 41.89–59.77% | 10 / 14 | 0.51usd per problem | [matharena · arxiv--march](https://matharena.ai/competition_tables/arxiv--march) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 50.83 \| percent \| competition \| Higher is better \| \| `cost_per_problem` \| 0.51 \| usd_per_problem \| competition \| Lower is better \| ### Configuration competition arxiv--march predicted false Reasoning effort xhigh sourceModelName Claude-Opus-4.7 (xhigh) sourceModelVersion anthropic/opus_47 thinkingEnabled true ### Reported statistics Uncertainty 95% confidence interval: 41.89–59.77% confidenceInterval95 8.94 problems 30 ### Source [Original source](https://matharena.ai/competition_tables/arxiv--march) Source matharena Original model label Claude-Opus-4.7 (xhigh) Source version arxiv--march Observed 2026-10-22T05:30:08.323Z Evidence SHA-256 `9cb6d9cc26949fcb2b6affed792584b4bfe9d6168e1fc5cf2c13b38d3479715b` Source locator `/table/rows/10` |  |  |  |  |  |  |

---
Cite as: Claude Opus 4.7Extra high — Benchize, https://benchize.com/models/claude-opus-4-7-xhigh (retrieved 2026-10-22)