Code review
Results are only compared within a matching group, so a model tested one way is never ranked against a model tested another way.
Review a code change and catch the real bugs it introduces without burying them in invalid or low-value comments
Ranking groups use separate scales. Compare configurations only inside the same group; EvalRank never flattens unlike systems into one leaderboard.
ベンチマーク横断のコンセンサス
このトピックで採用されているベンチマーク全体でモデルを順位付けしたものです。意思決定のときと同じ重み付けを用いています。各スコアは、モデルの結果が最高結果に占める割合です。
| Rank | Model | Share of best | Benchmarks |
|---|---|---|---|
| 1 | GPT-6.1 Terra | 100.0% | 1 |
| 2 | GPT-6.1 Sol | 90.5% | 1 |
| 3 | Grok 4.6 | 89.7% | 1 |
| 4 | Gemini 3.8 Flash | 87.1% | 1 |
| 5 | Gemini 4 Argon | 86.6% | 1 |
| 6 | Claude Opus 5.5 | 86.3% | 1 |
| 7 | GPT-6 Sol | 85.2% | 1 |
| 8 | Claude Opus 5 | 80.7% | 1 |
| 9 | GPT-6 Luna | 76.8% | 1 |
エージェントシステム · エージェンティック
Exploratory - not a ranked winner yetrg-code-review-agent-system-agentic-agent-system-v1エクスプローラーのエビデンス
MacroscopeBench, every reasoning effort (Macroscope)
Sources differ; shown separately, never averaged。に確認しました。まで有効です。
| Rank | Configuration | Capability | Uncertainty | Families |
|---|---|---|---|---|
| 1 | Claude Opus 5.5 macroscopebench:max-effortconfig_e6d73883b79a458bb42954a12f9a4bd2f61b19d1a69dbedddcee57a7ccfc3a20 | 100% | 不明 | 1 |
| 2 | GPT-6.1 Terra macroscopebench:high-effortconfig_0fca9081059f9ea84ea730e704c71ba4a674756223e8349e7fb8c727c9279e18 | 96% | 不明 | 1 |
| 3 | GPT-6.1 Terra macroscopebench:medium-effortconfig_c3d1dc0e44423d43a98bc671e568d383d8cef0d30029eb2e6b34adb2bb3ffb5e | 93% | 不明 | 1 |
| 4 | GPT-6 Sol macroscopebench:max-effortconfig_8355540786508f62b7649c7e41ab7c7c3840eb783dc6fa18f30fa4ebf7f69482 | 91% | 不明 | 1 |
| 5 | Claude Opus 5.5 macroscopebench:xhigh-effortconfig_8b30978b3842998bf9bbb38614b78c91c8e326d7807192a9af2c2988cda4e00f | 87% | 不明 | 1 |
| 6 | GPT-6.1 Sol macroscopebench:max-effortconfig_78df30b801e7eb04d6ef351803a5b54130f7c6a7b4d5ff9aa9756422418d076d | 86% | 不明 | 1 |
| 7 | GPT-6 Astra macroscopebench:max-effortconfig_a75d727f10d4a0eac19d6e01bf487c6184e8a510672183ea02a01a5fc23f3c8f | 85% | 不明 | 1 |
| 8 | GPT-5.6 Sol macroscopebench:high-effortconfig_99f8f7f0f456b8c6d1df1fa7043c58df55379cef41fa8a486e932ad43c3dfaca | 84% | 不明 | 1 |
| 9 | GLM 5.3 macroscopebench:max-effortconfig_483032ccc1d3f89ac4535ef6e623763c1cf3e47b0f87f7636ef89ca557e32604 | 83% | 不明 | 1 |
| 10 | GPT-6.1 Sol macroscopebench:xhigh-effortconfig_82926d8185ff4aefa885e0248125762b7364ee16ea39e3de6323d76c6420dbfb | 83% | 不明 | 1 |
| 11 | GPT-6 Sol macroscopebench:xhigh-effortconfig_b5112dbc3d69b149f10e0a3d43ec90644a4a03cb6431d7441b6cd137f4d727e3 | 83% | 不明 | 1 |
| 12 | GPT-6.1 Sol macroscopebench:high-effortconfig_5a24f76c989220b98e8d8a772ebe10c60ec362db74a637fec8cbe6db7ddc6300 | 82% | 不明 | 1 |
| 13 | GPT-6.1 Terra macroscopebench:low-effortconfig_91304552afd01f5c37cfc14bc2b27d07892f9db62ffe0fbff8d4206288f68ae8 | 80% | 不明 | 1 |
| 14 | Grok 4.6 macroscopebench:xhigh-effortconfig_40f36156eaa01fa3d0fa03fe65b5d085cd5e91e64eeff83efcb02980d3ba0628 | 80% | 不明 | 1 |
| 15 | Grok 4.6 macroscopebench:high-effortconfig_9c445642dfb058b00be7b564987b4f27af2bff78275a8d43bda504fd245abf43 | 78% | 不明 | 1 |
| 16 | GPT-6 Sol macroscopebench:high-effortconfig_e25f44e408a733401428874642e5edfe2bf935f05a41052f7ab74ee0fbb99318 | 76% | 不明 | 1 |
| 17 | GPT-6.1 Sol macroscopebench:medium-effortconfig_9dafacf26cdd886ba1c1f49d87065b7d3f5cd54feb06f8ad8d6638188d37d663 | 73% | 不明 | 1 |
| 18 | Claude Opus 5.5 macroscopebench:high-effortconfig_733dd5cc9437841e5449fa06b422c17e83334f55168c2f5d5b9325a535289ffc | 72% | 不明 | 1 |
| 19 | Kimi K3 macroscopebench:max-effortconfig_fc2b52a594c8a99a3b7c2b59e1391c3c83620d834ea81943588d979eda112be6 | 72% | 不明 | 1 |
| 20 | Grok 4.6 macroscopebench:medium-effortconfig_10f0ba0fa4acbaba4d1227648e8a00f2cb7bc77f44f64a7b4ccf1880e161daf2 | 72% | 不明 | 1 |
| 21 | Gemini 4 Argon macroscopebench:high-effortconfig_530c748fedff86cf7de491f4118d6c8a2c4dd2493b47a2cced04258747e2abf5 | 72% | 不明 | 1 |
| 22 | GPT-6 Luna macroscopebench:max-effortconfig_3c0dd5fe33609fcaddb22f06a3e078e4f268b2003568cc116ae7eb7384151607 | 71% | 不明 | 1 |
| 23 | DeepSeek V4.1 Flash macroscopebench:max-effortconfig_1b29e838bc883e7f200532f0c15b9414fcb38a2e33e878b81ffa9203b1f651e2 | 70% | 不明 | 1 |
| 24 | Gemini 3.8 Flash macroscopebench:medium-effortconfig_9da81bf684efbe1ad1948d51b5b78cb6cd93e9dad9c50d8fc7887883e3a32b50 | 66% | 不明 | 1 |
| 25 | DeepSeek V4.1 Flash macroscopebench:low-effortconfig_ce17896acd252f51af585df90ee2ec0e3d45888ceb07c6a1dd33a711252d6ed4 | 66% | 不明 | 1 |
| 26 | GPT-6.1 Sol macroscopebench:low-effortconfig_7c8deb8f693e6c268a2313d787bf120b0ea2e5f62cd4f1417060353ee57317f8 | 66% | 不明 | 1 |
| 27 | DeepSeek V4.1 Flash macroscopebench:high-effortconfig_2b2e93dfccd56f89985469205995a700afa68ca234cb33876dd8bebc4d1b4b49 | 66% | 不明 | 1 |
| 28 | Gemini 4 Argon macroscopebench:medium-effortconfig_d54438a864b253c5bd74a5728f3089cefd93808fcbd5b5037bffb483fbb03af1 | 65% | 不明 | 1 |
| 29 | Claude Opus 5.5 macroscopebench:medium-effortconfig_81b476353cd67c47751bf44dac77ad0f9eee84f3498f3c8b89f694420f430ff3 | 65% | 不明 | 1 |
| 30 | Claude Opus 5 macroscopebench:high-effortconfig_88f804bb21b203128d39a5f2c65aac58f46eaf269947654a8c16b50f2d1a8219 | 64% | 不明 | 1 |
| 31 | GLM 5.3 macroscopebench:high-effortconfig_f8c73c8a27ed8ec1ddba264606a44cea6f03daac9b87b51d8be381f565cbeb04 | 63% | 不明 | 1 |
| 32 | GPT-6 Sol macroscopebench:medium-effortconfig_60c27177bb62cbb0bc1a1315c3195c7739acd13b0107510df793d173238ae34f | 63% | 不明 | 1 |
| 33 | Kimi K3 macroscopebench:high-effortconfig_9197026ae1add69be5447726f323c3b6df043eaf50ff17785efd62297e0def15 | 61% | 不明 | 1 |
| 34 | GPT-6 Luna macroscopebench:xhigh-effortconfig_88e3c4fc4945be6778e224c4012ab03451b10e72c22e0ee09ea2182d94eb2703 | 60% | 不明 | 1 |
| 35 | GPT-5.6 Sol macroscopebench:low-effortconfig_accd884ef51fabc161a52d15d9b4db38cca243783d42ed7108a2f8b5d73a3402 | 55% | 不明 | 1 |
| 36 | GPT-6 Luna macroscopebench:high-effortconfig_82058abb9bbc34aa1c34ae904cca0e264290b8f3b3f4e00bd6a94f4416e17652 | 53% | 不明 | 1 |
| 37 | Claude Opus 5 macroscopebench:medium-effortconfig_88aafab5a5dd6c8836dce41a23b99df08d5a0740972946670a44b907435db23b | 53% | 不明 | 1 |
| 38 | Muse Wonder macroscopebench:low-effortconfig_56cc703ca619ffb3e91db893245ecd9cbcce726abcaf09352122dfdf63726f56 | 50% | 不明 | 1 |
| 39 | GPT-6 Luna macroscopebench:medium-effortconfig_29792f84f3e1cb2bc35c50d8e07675f7a7d08a8e1772251c5544842835e305ba | 45% | 不明 | 1 |
| 40 | GPT-6 Sol macroscopebench:low-effortconfig_ef2e7cca45952dfa1c5f5bb88e5a50eb9988bf57d5be8e41595685154337e61f | 44% | 不明 | 1 |
| 41 | Claude Opus 5.5 macroscopebench:low-effortconfig_0c2ade372c70318cb921a18ade2cfc1572dc5691bf9b7db84d5b9bb1f4c19160 | 43% | 不明 | 1 |
| 42 | Gemini 4 Argon macroscopebench:low-effortconfig_9f37b46f7c7caa07013c896b1c888f7c6cc019824df18eb87c248740acd08540 | 42% | 不明 | 1 |
| 43 | Claude Opus 5 macroscopebench:low-effortconfig_db91574819230d1677188be05a134058093d98912c162f534aff9147cb2b76e9 | 38% | 不明 | 1 |
| 44 | Grok 4.6 macroscopebench:low-effortconfig_3368cc140fbfd7ce4dadd75a37bb9e79ffa5019153bd0554318a22c185f860cb | 32% | 不明 | 1 |
| 45 | GLM 5.3 macroscopebench:low-effortconfig_888ee1fd139c4c552ceab0300b8ab5cd4d374e6a23f8b8f36006393e328f593b | 25% | 不明 | 1 |
| 46 | Kimi K3 macroscopebench:low-effortconfig_7aab349be7a0f827ef808b8c22a1e74af5ea0f2d625d7b523b9fb39ed3d32db7 | 22% | 不明 | 1 |
| 47 | Gemini 3.8 Flash macroscopebench:low-effortconfig_02e963f4bb6cd6a43724fd3a7e10a67dc2f157f877b244978c1d858c2e24d18d | 17% | 不明 | 1 |
| 48 | GPT-6 Luna macroscopebench:low-effortconfig_246e3f618910cca9f31cb112d2ec39ccdad228a931a1c22d0b5fd7430147faaf | 0% | 不明 | 1 |
出典：Macroscope
エクスプローラーのエビデンス
MacroscopeBench, medium effort (Macroscope)
Sources differ; shown separately, never averaged。に確認しました。まで有効です。
| Rank | Configuration | Capability | Uncertainty | Families |
|---|---|---|---|---|
| 1 | GPT-6.1 Terra macroscopebench:medium-effortconfig_c3d1dc0e44423d43a98bc671e568d383d8cef0d30029eb2e6b34adb2bb3ffb5e | 100% | 不明 | 1 |
| 2 | GPT-6.1 Sol macroscopebench:medium-effortconfig_9dafacf26cdd886ba1c1f49d87065b7d3f5cd54feb06f8ad8d6638188d37d663 | 59% | 不明 | 1 |
| 3 | Grok 4.6 macroscopebench:medium-effortconfig_10f0ba0fa4acbaba4d1227648e8a00f2cb7bc77f44f64a7b4ccf1880e161daf2 | 55% | 不明 | 1 |
| 4 | Gemini 3.8 Flash macroscopebench:medium-effortconfig_9da81bf684efbe1ad1948d51b5b78cb6cd93e9dad9c50d8fc7887883e3a32b50 | 44% | 不明 | 1 |
| 5 | Gemini 4 Argon macroscopebench:medium-effortconfig_d54438a864b253c5bd74a5728f3089cefd93808fcbd5b5037bffb483fbb03af1 | 42% | 不明 | 1 |
| 6 | Claude Opus 5.5 macroscopebench:medium-effortconfig_81b476353cd67c47751bf44dac77ad0f9eee84f3498f3c8b89f694420f430ff3 | 41% | 不明 | 1 |
| 7 | GPT-6 Sol macroscopebench:medium-effortconfig_60c27177bb62cbb0bc1a1315c3195c7739acd13b0107510df793d173238ae34f | 36% | 不明 | 1 |
| 8 | Claude Opus 5 macroscopebench:medium-effortconfig_88aafab5a5dd6c8836dce41a23b99df08d5a0740972946670a44b907435db23b | 16% | 不明 | 1 |
| 9 | GPT-6 Luna macroscopebench:medium-effortconfig_29792f84f3e1cb2bc35c50d8e07675f7a7d08a8e1772251c5544842835e305ba | 0% | 不明 | 1 |
出典：Macroscope
上位セットを定めるための独立したエビデンスが不足しています。
- キャリブレーションが検証されていません。
- 独立したベンチマークファミリーのカバレッジが基準値を下回っています。