init: seed framework reference content from agent-runtimes main repo

model-registry/airouter-qwen3.yaml

@@ -0,0 +1,14 @@
+name: airouter-qwen3
+endpoint: airouter-qwen3
+scores:
+  complexity: 8
+  test_pass_rate: 7
+  creativity: 7
+  spec_adherence: 7
+  cost_efficiency: 10
+  context_utilisation: 8
+cost_per_1k_tokens:
+  input: 0.0
+  output: 0.0
+source: benchmark
+harness_version: null

model-registry/claude-haiku-4.yaml

@@ -0,0 +1,14 @@
+name: claude-haiku-4
+endpoint: claude-haiku-4
+scores:
+  complexity: 5
+  test_pass_rate: 7
+  creativity: 6
+  spec_adherence: 8
+  cost_efficiency: 9
+  context_utilisation: 6
+cost_per_1k_tokens:
+  input: 0.0008
+  output: 0.004
+source: benchmark
+harness_version: null

model-registry/claude-opus-4.yaml

@@ -0,0 +1,14 @@
+name: claude-opus-4
+endpoint: claude-opus-4
+scores:
+  complexity: 10
+  test_pass_rate: 9
+  creativity: 10
+  spec_adherence: 9
+  cost_efficiency: 3
+  context_utilisation: 10
+cost_per_1k_tokens:
+  input: 0.015
+  output: 0.075
+source: benchmark
+harness_version: null

model-registry/claude-sonnet-4.yaml

@@ -0,0 +1,14 @@
+name: claude-sonnet-4
+endpoint: claude-sonnet-4
+scores:
+  complexity: 8
+  test_pass_rate: 9
+  creativity: 8
+  spec_adherence: 9
+  cost_efficiency: 6
+  context_utilisation: 8
+cost_per_1k_tokens:
+  input: 0.003
+  output: 0.015
+source: benchmark
+harness_version: null

model-registry/github-models-gpt4o.yaml

@@ -0,0 +1,14 @@
+name: github-models-gpt4o
+endpoint: github-models-gpt4o
+scores:
+  complexity: 8
+  test_pass_rate: 8
+  creativity: 8
+  spec_adherence: 8
+  cost_efficiency: 7
+  context_utilisation: 8
+cost_per_1k_tokens:
+  input: 0.0
+  output: 0.0
+source: benchmark
+harness_version: null

model-registry/gpt-4o-openai.yaml

@@ -0,0 +1,14 @@
+name: gpt-4o-openai
+endpoint: gpt-4o-openai
+scores:
+  complexity: 8
+  test_pass_rate: 8
+  creativity: 8
+  spec_adherence: 8
+  cost_efficiency: 7
+  context_utilisation: 8
+cost_per_1k_tokens:
+  input: 0.0025
+  output: 0.01
+source: benchmark
+harness_version: null

model-registry/opencode-zen-sonnet.yaml

@@ -0,0 +1,14 @@
+name: opencode-zen-sonnet
+endpoint: opencode-zen-sonnet
+scores:
+  complexity: 8
+  test_pass_rate: 9
+  creativity: 8
+  spec_adherence: 9
+  cost_efficiency: 6
+  context_utilisation: 8
+cost_per_1k_tokens:
+  input: 0.003
+  output: 0.015
+source: benchmark
+harness_version: null

model-registry/openrouter-sonnet.yaml

@@ -0,0 +1,14 @@
+name: openrouter-sonnet
+endpoint: openrouter-sonnet
+scores:
+  complexity: 8
+  test_pass_rate: 9
+  creativity: 8
+  spec_adherence: 9
+  cost_efficiency: 6
+  context_utilisation: 8
+cost_per_1k_tokens:
+  input: 0.003
+  output: 0.015
+source: benchmark
+harness_version: null

model-registry/qwen3-235b.yaml

@@ -0,0 +1,14 @@
+name: qwen3-235b
+endpoint: qwen3-235b-vllm
+scores:
+  complexity: 8
+  test_pass_rate: 8
+  creativity: 7
+  spec_adherence: 8
+  cost_efficiency: 8
+  context_utilisation: 7
+cost_per_1k_tokens:
+  input: 0.0002
+  output: 0.0006
+source: benchmark
+harness_version: null