すべてのベンチマーク

モデルルーティングのベンチマーク

モデルルーター、複合モデル、その他の種類のマルチモデル切り替えロジックの性能を比較できます。

Auto Router は Jev Router を搭載するようになりました。 仕組みを見る →
ルーター
nvidia のファビコン
openrouter のファビコン
sakana のファビコン
unbiased のファビコン
6 個のルーター
Auto、Fugu Max、Pareto、Auto Code、Fugu Ultra v2 と Switchyard によるモデル切り替え
モデル
anthropic のファビコン
deepseek のファビコン
google のファビコン
moonshotai のファビコン
18 個のモデル
ルートモデルとベースラインモデルのみで、ルーターモデルの選択肢は利用できません
結果
162
公開済みのルーターとベースラインの実行

ベンチマークの最終実行

モデルルーティングのフロンティア

デフォルトでは、各点はベンチマーク全体で平均したモデルルーターの品質を表します。マトリックス内のモデルルーティング指標とは異なり、コストと速度は品質に組み込まれず、横軸に表示されます。ベンチマークを選択してそのベンチマークでの品質を比較するか、横軸で測定する項目を変更してください。

品質フロンティア

評価されたタスクごとの記録されたコストを対数スケールで示します。 品質スコアは、各ベンチマークで最良のルーターに対する相対的な精度(0–10)を、ベンチマーク全体で平均した値です。すべてのルーターを上回るベースラインのスコアは、上限を 10 とします。 白抜きの点は単一モデルのベースラインで、参考として表示しています。 スコアが軸の下限を下回るベースラインは表示しませんが、結果テーブルには引き続き含まれます。

品質フロンティア
モデルルーター品質スコアコスト / タスク
Claude Haiku 5.5 (low)3.5$0.053
Claude Haiku 5.5 (medium)4.7$0.098
Switchyard · Claude Opus 5.5 + Claude Sonnet 5.5 (high)8.2$3.02
Claude Opus 5.5 (high)9.1$6.43
Claude Opus 5.5 (low)6.7$0.46
Claude Opus 5.5 (medium)8.1$0.98
Claude Sonnet 5.5 (high)7.5$0.83
Claude Sonnet 5.5 (low)4.8$0.22
Claude Sonnet 5.5 (medium)5.4$0.29
Claude Sonnet 5.58.1$0.92
Switchyard · Deepseek v4.1 Flash + GPT-6-Sol (high)8.4$0.36
Deepseek v4.1 Flash (high)7.9$0.22
Deepseek v4.1 Flash (max)8.2$0.20
Deepseek v4.1 Flash6.7$1.02
Gemini 4 Argon (high)9.3$1.33
Kimi K3 (high)8.9$0.93
Kimi K3 (low)7.4$0.67
Kimi K3.1 Pro (high)9.6$0.50
Kimi K3.1 Pro9.0$2.66
Switchyard · GPT-6-Astra + GPT-6.1-Sol (high)8.6$2.17
GPT-6-Astra (high)9.0$1.73
GPT-6-Astra (low)7.6$1.02
GPT-6-Astra (medium)8.0$1.70
GPT-6-Luna (high)6.5$0.040
GPT-6-Luna (max)7.6$0.074
GPT-6-Luna3.4$0.062
Switchyard · GPT-6-Sol + GPT-6-Astra (high)9.2$1.56
GPT-6-Sol (high)8.5$0.34
Switchyard · GPT-6.1-Sol + GPT-6-Luna (high)7.2$0.37
GPT-6.1-Sol (high)8.2$0.38
GPT-6.1-Sol (low)6.9$0.14
GPT-6.1-Sol (medium)8.4$0.25
GPT-6.1-Terra (high)8.3$0.21
Grok 4.7 (medium)7.0$3.21
Mimo v2.6 Pro (xhigh)7.8$0.15
GLM 5.3 (high)8.0$0.77
Switchyard · GLM 5.3 Flash + Claude Opus 5.5 (high)8.8$1.01
GLM 5.3 Flash (high)6.5$0.15
GLM 5.3 Flash9.3$0.29
Auto (Medium tier)9.3$0.58
Auto Code9.8$1.64
Fugu Max6.8$1.29
Pareto8.6$0.16
Deepseek v4.1 Flash 1017 (high)7.3$0.044
Gemini 3.8 Flash (high)8.6$0.26
Fugu Ultra v28.8$3.95
Claude Haiku 5.5 (high)4.9$0.048
Switchyard · Gemini 4 Argon + Gemini 3.8 Flash (high)8.2$0.70

ベンチマークマトリックス

モデルルーティング指標は、品質、速度、コストを組み合わせ、各ベンチマークの最高結果を基準とした 0–10 のスコアで表します。 モデルルーティングのフロンティアを探索.

モデルルーター
ルーター
Auto
Deep SWE69.0%
SWE Atlas QA59.7%
Terminal Bench 4.045.7%
Tau3 Bankingベンチマークで最高53.1%
MMMU Pro Vision80.1%
Auto Code
Deep SWE74.3%
SWE Atlas QA62.5%
Terminal Bench 4.0ベンチマークで最高50.0%
Tau3 Banking52.6%
MMMU Pro Vision82.3%
Fugu Max
Deep SWE33.9%
SWE Atlas QA52.4%
Terminal Bench 4.0—
Tau3 Banking29.9%
MMMU Pro Vision79.5%
Fugu Ultra v2
Deep SWE—
SWE Atlas QAベンチマークで最高69.5%
Terminal Bench 4.0—
Tau3 Banking35.1%
MMMU Pro Vision80.5%
Pareto
Deep SWE74.3%
SWE Atlas QA60.5%
Terminal Bench 4.042.5%
Tau3 Banking35.1%
MMMU Pro Vision75.5%
複数モデルの切り替え
Switchyard
アルゴリズム:ステージ
Claude Opus 5.5 + Claude Sonnet 5.5 (high)
Deep SWE68.8%
SWE Atlas QA56.5%
Terminal Bench 4.045.0%
Tau3 Banking35.1%
MMMU Pro Vision—
Deepseek v4.1 Flash + GPT-6-Sol (high)
Deep SWE65.5%
SWE Atlas QA52.9%
Terminal Bench 4.0—
Tau3 Banking41.2%
MMMU Pro Vision77.0%
Gemini 4 Argon + Gemini 3.8 Flash (high)
Deep SWE—
SWE Atlas QA60.5%
Terminal Bench 4.035.0%
Tau3 Banking47.4%
MMMU Pro Vision—
GLM 5.3 Flash + Claude Opus 5.5 (high)
Deep SWE73.5%
SWE Atlas QA59.7%
Terminal Bench 4.0—
Tau3 Banking38.1%
MMMU Pro Vision79.5%
GPT-6-Astra + GPT-6.1-Sol (high)
Deep SWE73.5%
SWE Atlas QA—
Terminal Bench 4.045.0%
Tau3 Banking38.1%
MMMU Pro Vision—
GPT-6-Sol + GPT-6-Astra (high)
Deep SWE70.8%
SWE Atlas QA66.1%
Terminal Bench 4.0—
Tau3 Banking42.3%
MMMU Pro Visionベンチマークで最高82.4%
GPT-6.1-Sol + GPT-6-Luna (high)
Deep SWEベンチマークで最高75.2%
SWE Atlas QA—
Terminal Bench 4.033.3%
Tau3 Banking26.8%
MMMU Pro Vision—
単一モデルのベースライン(参考)
Claude Haiku 5.5 (high)
Deep SWE—
SWE Atlas QA43.5%
Terminal Bench 4.0—
Tau3 Banking18.6%
MMMU Pro Vision—
Claude Haiku 5.5 (low)
Deep SWE40.7%
SWE Atlas QA24.2%
Terminal Bench 4.0—
Tau3 Banking9.3%
MMMU Pro Vision—
Claude Haiku 5.5 (medium)
Deep SWE52.2%
SWE Atlas QA31.5%
Terminal Bench 4.0—
Tau3 Banking14.4%
MMMU Pro Vision—
Claude Opus 5.5 (high)
Deep SWE70.5%
SWE Atlas QA55.6%
Terminal Bench 4.053.1%
Tau3 Banking42.3%
MMMU Pro Vision81.8%
Claude Opus 5.5 (low)
Deep SWE61.1%
SWE Atlas QA39.5%
Terminal Bench 4.0—
Tau3 Banking33.5%
MMMU Pro Vision—
Claude Opus 5.5 (medium)
Deep SWE67.7%
SWE Atlas QA54.0%
Terminal Bench 4.0—
Tau3 Banking39.7%
MMMU Pro Vision—
Claude Sonnet 5.5
Deep SWE77.8%
SWE Atlas QA—
Terminal Bench 4.031.3%
Tau3 Banking—
MMMU Pro Vision—
Claude Sonnet 5.5 (high)
Deep SWE66.4%
SWE Atlas QA48.4%
Terminal Bench 4.0—
Tau3 Banking35.6%
MMMU Pro Vision—
Claude Sonnet 5.5 (low)
Deep SWE54.0%
SWE Atlas QA20.2%
Terminal Bench 4.0—
Tau3 Banking22.2%
MMMU Pro Vision—
Claude Sonnet 5.5 (medium)
Deep SWE49.6%
SWE Atlas QA33.1%
Terminal Bench 4.0—
Tau3 Banking25.3%
MMMU Pro Vision—
Deepseek v4.1 Flash
Deep SWE63.6%
SWE Atlas QA—
Terminal Bench 4.025.0%
Tau3 Banking—
MMMU Pro Vision—
Deepseek v4.1 Flash (high)
Deep SWE62.8%
SWE Atlas QA63.7%
Terminal Bench 4.0—
Tau3 Banking32.5%
MMMU Pro Vision—
Deepseek v4.1 Flash (max)
Deep SWE61.9%
SWE Atlas QA65.3%
Terminal Bench 4.0—
Tau3 Banking36.1%
MMMU Pro Vision68.2%
Deepseek v4.1 Flash 1017 (high)
Deep SWE—
SWE Atlas QA58.1%
Terminal Bench 4.0—
Tau3 Banking24.7%
MMMU Pro Vision72.7%
Gemini 3.8 Flash (high)
Deep SWE—
SWE Atlas QA43.5%
Terminal Bench 4.0—
Tau3 Banking39.2%
MMMU Pro Vision81.5%
Gemini 4 Argon (high)
Deep SWE76.1%
SWE Atlas QA58.9%
Terminal Bench 4.0—
Tau3 Banking46.4%
MMMU Pro Vision87.0%
GLM 5.3 (high)
Deep SWE64.6%
SWE Atlas QA57.3%
Terminal Bench 4.0—
Tau3 Banking38.1%
MMMU Pro Vision—
GLM 5.3 Flash
Deep SWE84.6%
SWE Atlas QA—
Terminal Bench 4.042.9%
Tau3 Banking—
MMMU Pro Vision—
GLM 5.3 Flash (high)
Deep SWE31.0%
SWE Atlas QA42.7%
Terminal Bench 4.0—
Tau3 Banking34.0%
MMMU Pro Vision75.4%
GPT-6-Astra (high)
Deep SWE73.5%
SWE Atlas QA65.5%
Terminal Bench 4.0—
Tau3 Banking35.6%
MMMU Pro Vision84.2%
GPT-6-Astra (low)
Deep SWE67.2%
SWE Atlas QA54.1%
Terminal Bench 4.0—
Tau3 Banking32.5%
MMMU Pro Vision—
GPT-6-Astra (medium)
Deep SWE69.9%
SWE Atlas QA58.8%
Terminal Bench 4.0—
Tau3 Banking33.0%
MMMU Pro Vision—
GPT-6-Luna
Deep SWE51.2%
SWE Atlas QA—
Terminal Bench 4.00.0%
Tau3 Banking—
MMMU Pro Vision—
GPT-6-Luna (high)
Deep SWE53.1%
SWE Atlas QA35.5%
Terminal Bench 4.0—
Tau3 Banking24.2%
MMMU Pro Vision76.6%
GPT-6-Luna (max)
Deep SWE67.3%
SWE Atlas QA42.7%
Terminal Bench 4.0—
Tau3 Banking30.9%
MMMU Pro Vision77.3%
GPT-6-Sol (high)
Deep SWE61.1%
SWE Atlas QA55.4%
Terminal Bench 4.0—
Tau3 Banking42.3%
MMMU Pro Vision81.5%
GPT-6.1-Sol (high)
Deep SWE70.8%
SWE Atlas QA59.7%
Terminal Bench 4.0—
Tau3 Banking35.1%
MMMU Pro Vision—
GPT-6.1-Sol (low)
Deep SWE60.2%
SWE Atlas QA51.6%
Terminal Bench 4.0—
Tau3 Banking27.8%
MMMU Pro Vision—
GPT-6.1-Sol (medium)
Deep SWE72.6%
SWE Atlas QA60.5%
Terminal Bench 4.0—
Tau3 Banking37.1%
MMMU Pro Vision—
GPT-6.1-Terra (high)
Deep SWE72.8%
SWE Atlas QA53.6%
Terminal Bench 4.040.8%
Tau3 Banking33.0%
MMMU Pro Vision80.3%
Grok 4.7 (medium)
Deep SWE35.4%
SWE Atlas QA58.9%
Terminal Bench 4.0—
Tau3 Banking41.8%
MMMU Pro Vision—
Kimi K3 (high)
Deep SWE69.0%
SWE Atlas QA58.1%
Terminal Bench 4.0—
Tau3 Banking42.8%
MMMU Pro Vision81.0%
Kimi K3 (low)
Deep SWE57.5%
SWE Atlas QA—
Terminal Bench 4.0—
Tau3 Banking38.1%
MMMU Pro Vision—
Kimi K3.1 Pro
Deep SWE60.0%
SWE Atlas QA—
Terminal Bench 4.068.8%
Tau3 Banking—
MMMU Pro Vision—
Kimi K3.1 Pro (high)
Deep SWE77.9%
SWE Atlas QA58.1%
Terminal Bench 4.0—
Tau3 Banking54.6%
MMMU Pro Vision81.8%
Mimo v2.6 Pro (xhigh)
Deep SWE58.4%
SWE Atlas QA54.0%
Terminal Bench 4.0—
Tau3 Banking42.3%
MMMU Pro Vision63.6%
より良いより低い単一モデルのベースラインは参考として表示され、ランキングには含まれません。

モデルルーティングの結果

Deep SWE43 件の結果
Deep SWE GLM 5.3 Flash84.6%$0.20$0.2426.7m
Deep SWE Kimi K3.1 Pro77.9%$0.85$1.0918.6m
Deep SWE Claude Sonnet 5.577.8%$0.40$0.516.0m
Deep SWE Gemini 4 Argon76.1%$3.12$4.1026.6m
Deep SWE Switchyard · GPT-6.1-Sol + GPT-6-Luna (high)75.2%$0.47$0.6312.6m
Deep SWE Auto Code74.3%$1.98$2.6615.2m
Deep SWE Pareto74.3%$0.19$0.267.5m
Deep SWE Switchyard · GPT-6-Astra + GPT-6.1-Sol (high)73.5%$2.54$3.4612.5m
Deep SWE GPT-6-Astra73.5%$2.99$4.0711.7m
Deep SWE Switchyard · GLM 5.3 Flash + Claude Opus 5.5 (high)73.5%$2.47$3.3617.4m
Deep SWE GPT-6.1-Terra72.8%$0.31$0.438.3m
Deep SWE GPT-6.1-Sol · openai72.6%$0.30$0.413.7m
Deep SWE Switchyard · GPT-6-Sol + GPT-6-Astra (high)70.8%$2.35$3.328.5m
Deep SWE GPT-6.1-Sol (high)70.8%$0.46$0.656.5m
Deep SWE Claude Opus 5.570.5%$7.76$11.0051.9m
Deep SWE GPT-6-Astra69.9%$1.99$2.855.8m
Deep SWE Kimi K3 (high)69.0%$1.85$2.6823.1m
Deep SWE Auto (Medium tier)69.0%$0.57$0.839.6m
Deep SWE Switchyard · Claude Opus 5.5 + Claude Sonnet 5.5 (high)68.8%$6.59$9.5944.9m
Deep SWE Claude Opus 5.567.7%$1.54$2.277.0m
Deep SWE GPT-6-Luna67.3%$0.18$0.2717.7m
Deep SWE GPT-6-Astra67.2%$1.02$1.523.1m
Deep SWE Claude Sonnet 5.566.4%$1.86$2.8021.4m
Deep SWE Switchyard · Deepseek v4.1 Flash + GPT-6-Sol (high)65.5%$0.48$0.746.3m
Deep SWE GLM 5.3 (high)64.6%$1.46$2.2616.3m
Deep SWE Deepseek v4.1 Flash63.6%$0.21$0.3315.6m
Deep SWE Deepseek v4.1 Flash62.8%$0.37$0.6019.9m
Deep SWE Deepseek v4.1 Flash61.9%$0.42$0.6827.5m
Deep SWE Claude Opus 5.561.1%$0.52$0.852.6m
Deep SWE GPT-6-Sol61.1%$0.46$0.753.6m
Deep SWE GPT-6.1-Sol60.2%$0.14$0.233.7m
Deep SWE Kimi K3.1 Pro60.0%$1.43$2.3824.9m
Deep SWE Mimo v2.6 Pro58.4%$0.31$0.5343.2m
Deep SWE Kimi K357.5%$0.63$1.104.4m
Deep SWE Claude Sonnet 5.554.0%$0.36$0.664.9m
Deep SWE GPT-6-Luna53.1%$0.11$0.2115.8m
Deep SWE Claude Haiku 5.552.2%$0.25$0.4823.7m
Deep SWE GPT-6-Luna51.2%$0.091$0.1810.8m
Deep SWE Claude Sonnet 5.549.6%$0.51$1.037.0m
Deep SWE Claude Haiku 5.540.7%$0.14$0.3416.2m
Deep SWE Grok 4.735.4%$5.89$16.6412.2m
Deep SWE Fugu Max33.9%$3.00$8.8525.4m
Deep SWE GLM 5.3 Flash (high)31.0%$0.34$1.1027.0m
MMMU Pro Vision22 件の結果
MMMU Pro Vision Gemini 4 Argon87.0%$0.027$0.03136s
MMMU Pro Vision GPT-6-Astra84.2%$0.058$0.0698s
MMMU Pro Vision Switchyard · GPT-6-Sol + GPT-6-Astra (high)82.4%$0.041$0.0499s
MMMU Pro Vision Auto Code82.3%$0.025$0.0316s
MMMU Pro Vision Claude Opus 5.581.8%$0.026$0.0329s
MMMU Pro Vision Kimi K3.1 Pro81.8%$0.016$0.01929s
MMMU Pro Vision Gemini 3.8 Flash81.5%$0.023$0.02945s
MMMU Pro Vision GPT-6-Sol81.5%$0.013$0.0167s
MMMU Pro Vision Kimi K381.0%$0.021$0.02588s
MMMU Pro Vision Fugu Ultra v280.5%$0.11$0.1442s
MMMU Pro Vision GPT-6.1-Terra80.3%$0.006$0.0076s
MMMU Pro Vision Auto (Medium tier)80.1%$0.020$0.02437s
MMMU Pro Vision Switchyard · GLM 5.3 Flash + Claude Opus 5.5 (high)79.5%$0.017$0.02123s
MMMU Pro Vision Fugu Max79.5%$0.019$0.02424s
MMMU Pro Vision GPT-6-Luna77.3%$0.002$0.00338s
MMMU Pro Vision Switchyard · Deepseek v4.1 Flash + GPT-6-Sol (high)77.0%$0.011$0.01442s
MMMU Pro Vision GPT-6-Luna76.6%$0.00089$0.0018s
MMMU Pro Vision Pareto75.5%$0.015$0.01917s
MMMU Pro Vision GLM 5.3 Flash75.4%$0.0008$0.00133s
MMMU Pro Vision Deepseek v4.1 Flash 101772.7%$0.006$0.00949s
MMMU Pro Vision Deepseek v4.1 Flash68.2%$0.016$0.0232.1m
MMMU Pro Vision Mimo v2.6 Pro63.6%$0.011$0.0172.5m
SWE Atlas QA40 件の結果
SWE Atlas QA Fugu Ultra v269.5%$8.91$12.8215.5m
SWE Atlas QA Switchyard · GPT-6-Sol + GPT-6-Astra (high)66.1%$1.98$2.995.3m
SWE Atlas QA GPT-6-Astra (high)65.5%$2.06$3.144.8m
SWE Atlas QA Deepseek v4.1 Flash65.3%$0.16$0.2512.7m
SWE Atlas QA Deepseek v4.1 Flash63.7%$0.19$0.2911.0m
SWE Atlas QA Auto Code62.5%$0.66$1.054.3m
SWE Atlas QA Switchyard · Gemini 4 Argon + Gemini 3.8 Flash (high)60.5%$1.28$2.1112.6m
SWE Atlas QA GPT-6.1-Sol60.5%$0.22$0.363.7m
SWE Atlas QA Pareto60.5%$0.14$0.234.8m
SWE Atlas QA GPT-6.1-Sol59.7%$0.39$0.655.8m
SWE Atlas QA Switchyard · GLM 5.3 Flash + Claude Opus 5.5 (high)59.7%$0.87$1.467.1m
SWE Atlas QA Auto (Medium tier)59.7%$0.36$0.604.9m
SWE Atlas QA Gemini 4 Argon58.9%$1.25$2.1312.9m
SWE Atlas QA Grok 4.758.9%$1.44$2.445.3m
SWE Atlas QA GPT-6-Astra58.8%$1.63$2.774.1m
SWE Atlas QA Deepseek v4.1 Flash 101758.1%$0.095$0.165.7m
SWE Atlas QA Kimi K3 (high)58.1%$0.86$1.498.1m
SWE Atlas QA Kimi K3.1 Pro58.1%$0.47$0.809.5m
SWE Atlas QA GLM 5.3 (high)57.3%$0.64$1.139.1m
SWE Atlas QA Switchyard · Claude Opus 5.5 + Claude Sonnet 5.5 (high)56.5%$0.80$1.427.0m
SWE Atlas QA Claude Opus 5.5 (high)55.6%$0.79$1.433.8m
SWE Atlas QA GPT-6-Sol (high)55.4%$0.35$0.642.6m
SWE Atlas QA GPT-6-Astra54.1%$0.89$1.642.6m
SWE Atlas QA Claude Opus 5.554.0%$0.48$0.892.8m
SWE Atlas QA Mimo v2.6 Pro54.0%$0.15$0.2820.4m
SWE Atlas QA GPT-6.1-Terra53.6%$0.16$0.293.6m
SWE Atlas QA Switchyard · Deepseek v4.1 Flash + GPT-6-Sol (high)52.9%$0.36$0.683.7m
SWE Atlas QA Fugu Max52.4%$1.56$2.9811.1m
SWE Atlas QA GPT-6.1-Sol51.6%$0.13$0.252.6m
SWE Atlas QA Claude Sonnet 5.548.4%$0.26$0.543.2m
SWE Atlas QA Claude Haiku 5.543.5%$0.048$0.115.7m
SWE Atlas QA Gemini 3.8 Flash

失敗

43.5%$1.04$2.409.8m
SWE Atlas QA GPT-6-Luna42.7%$0.064$0.157.8m
SWE Atlas QA GLM 5.3 Flash (high)42.7%$0.20$0.4615.1m
SWE Atlas QA Claude Opus 5.539.5%$0.16$0.4167s
SWE Atlas QA GPT-6-Luna (high)35.5%$0.027$0.0772.8m
SWE Atlas QA Claude Sonnet 5.533.1%$0.098$0.3089s
SWE Atlas QA Claude Haiku 5.531.5%$0.015$0.0482.5m
SWE Atlas QA Claude Haiku 5.524.2%$0.007$0.03087s
SWE Atlas QA Claude Sonnet 5.520.2%$0.069$0.3468s
Tau3 Banking43 件の結果
Tau3 Banking Kimi K3.1 Pro54.6%$0.66$1.216.0m
Tau3 Banking Auto (Medium tier)53.1%$0.60$1.135.4m
Tau3 Banking Auto Code52.6%$0.60$1.135.9m
Tau3 Banking Switchyard · Gemini 4 Argon + Gemini 3.8 Flash (high)47.4%$0.74$1.577.0m
Tau3 Banking Gemini 4 Argon46.4%$0.94$2.0310.5m
Tau3 Banking Kimi K342.8%$0.97$2.273.4m
Tau3 Banking Claude Opus 5.542.3%$0.98$2.321.9m
Tau3 Banking Switchyard · GPT-6-Sol + GPT-6-Astra (high)42.3%$1.86$4.412.6m
Tau3 Banking GPT-6-Sol (high)42.3%$0.55$1.291.6m
Tau3 Banking Mimo v2.6 Pro42.3%$0.12$0.2911.3m
Tau3 Banking Grok 4.741.8%$2.32$5.554.5m
Tau3 Banking Switchyard · Deepseek v4.1 Flash + GPT-6-Sol (high)41.2%$0.59$1.432.8m
Tau3 Banking Claude Opus 5.539.7%$0.92$2.321.8m
Tau3 Banking Gemini 3.8 Flash39.2%$0.50$1.274.2m
Tau3 Banking Kimi K338.1%$0.71$1.862.6m
Tau3 Banking Switchyard · GPT-6-Astra + GPT-6.1-Sol (high)38.1%$1.37$3.602.4m
Tau3 Banking GLM 5.3 (high)38.1%$0.19$0.491.9m
Tau3 Banking Switchyard · GLM 5.3 Flash + Claude Opus 5.5 (high)38.1%$0.67$1.743.8m
Tau3 Banking GPT-6.1-Sol37.1%$0.23$0.6267s
Tau3 Banking Deepseek v4.1 Flash36.1%$0.20$0.5617.9m
Tau3 Banking Claude Sonnet 5.535.6%$0.36$1.0165s
Tau3 Banking GPT-6-Astra35.6%$1.83$5.142.1m
Tau3 Banking Switchyard · Claude Opus 5.5 + Claude Sonnet 5.5 (high)35.1%$0.78$2.221.7m
Tau3 Banking GPT-6.1-Sol35.1%$0.30$0.861.5m
Tau3 Banking Fugu Ultra v235.1%$2.84$8.114.1m
Tau3 Banking Pareto35.1%$0.15$0.441.7m
Tau3 Banking GLM 5.3 Flash34.0%$0.043$0.1378s
Tau3 Banking Claude Opus 5.533.5%$0.69$2.0785s
Tau3 Banking GPT-6-Astra33.0%$1.49$4.5188s
Tau3 Banking GPT-6.1-Terra33.0%$0.17$0.5376s
Tau3 Banking Deepseek v4.1 Flash32.5%$0.11$0.337.5m
Tau3 Banking GPT-6-Astra32.5%$1.16$3.5881s
Tau3 Banking GPT-6-Luna30.9%$0.046$0.153.8m
Tau3 Banking Fugu Max29.9%$0.59$1.983.3m
Tau3 Banking GPT-6.1-Sol27.8%$0.16$0.5857s
Tau3 Banking Switchyard · GPT-6.1-Sol + GPT-6-Luna (high)26.8%$0.21$0.782.6m
Tau3 Banking Claude Sonnet 5.525.3%$0.27$1.0852s
Tau3 Banking Deepseek v4.1 Flash 101724.7%$0.032$0.132.2m
Tau3 Banking GPT-6-Luna24.2%$0.020$0.0831.5m
Tau3 Banking Claude Sonnet 5.522.2%$0.24$1.0847s
Tau3 Banking Claude Haiku 5.518.6%$0.048$0.2678s
Tau3 Banking Claude Haiku 5.514.4%$0.025$0.1859s
Tau3 Banking Claude Haiku 5.59.3%$0.016$0.1747s
Terminal Bench 4.014 件の結果
Terminal Bench 4.0 Kimi K3.1 Pro68.8%$3.90$5.6773.3m
Terminal Bench 4.0 Claude Opus 5.553.1%$22.60$35.72198.6m
Terminal Bench 4.0 Auto Code50.0%$4.96$6.6570.8m
Terminal Bench 4.0 Auto (Medium tier)45.7%$1.33$2.4025.1m
Terminal Bench 4.0 Switchyard · Claude Opus 5.5 + Claude Sonnet 5.5 (high)45.0%$3.89$8.6550.2m
Terminal Bench 4.0 Switchyard · GPT-6-Astra + GPT-6.1-Sol (high)45.0%$2.60$5.7813.0m
Terminal Bench 4.0 GLM 5.3 Flash42.9%$0.39$0.9185.9m
Terminal Bench 4.0 Pareto42.5%$0.29$0.6922.8m
Terminal Bench 4.0 GPT-6.1-Terra40.8%$0.40$0.9823.8m
Terminal Bench 4.0 Switchyard · Gemini 4 Argon + Gemini 3.8 Flash (high)35.0%$0.083$0.2457.4m
Terminal Bench 4.0 Switchyard · GPT-6.1-Sol + GPT-6-Luna (high)33.3%$0.44$1.3311.9m
Terminal Bench 4.0 Claude Sonnet 5.531.3%$1.44$4.6159.2m
Terminal Bench 4.0 Deepseek v4.1 Flash25.0%$1.84$7.34148.3m
Terminal Bench 4.0 GPT-6-Luna0.0%$0.033--30.2m