Skip to content
This repository was archived by the owner on Apr 23, 2026. It is now read-only.

Update LMArena English scores for Claude 4.6 and GPT 5.4 High #301

Merged
insign merged 2 commits into from
Apr 18, 2026
Merged

Update LMArena English scores for Claude 4.6 and GPT 5.4 High #301

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
a243f72
Update LMArena English Elo for top tier models
google-labs-jules[bot] Apr 18, 2026
d3766dd
Add Claude Opus 4.7 models and scores
google-labs-jules[bot] Apr 18, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
123 changes: 119 additions & 4 deletions data/showdown.json
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,7 +1,7 @@
{
"meta": {
"version": "2026.04.16",
"last_update": "2026-04-16T17:00:00Z",
"last_update": "2026-04-18T19:00:00Z",
"schema_version": "1.0"
},
"models": [
Expand Down Expand Up @@ -119,6 +119,121 @@
"arc_agi_2": 4.9
}
},
{
"id": "claude-opus-4-7-20260401-thinking-32k",
"name": "Claude 4.7 Opus Thinking",
"aka": ["claude-opus-4-7-thinking", "claude-4.7-opus-thinking", "claude-opus-4-7-max"],
"superior_of": "claude-opus-4-7-20260401",
"provider": "Anthropic",
"type": "proprietary",
"release_date": "2026-04-01",
"pricing": {
"input_per_1m": 5.0,
"output_per_1m": 25.0,
"average_per_1m": 10.0
},
"performance": {
"output_speed_tps": 50,
"latency_ttft_ms": 0,
"source": "https://artificialanalysis.ai/models/claude-opus-4-7"
},
"editor_notes": "Thinking mode for Claude 4.7 Opus. Takes the #1 overall spot on LMArena.",
"benchmark_scores": {
"lmarena_en_elo": 1505,
"lmarena_coding_elo": null,
"lmarena_hard_elo": null,
"lmarena_math_elo": null,
"lmarena_creative_elo": null,
"lmarena_if_elo": null,
"swe_bench": null,
"swe_bench_pro": null,
"gpqa_diamond": null,
"humanity_last_exam": null,
"livebench": null,
"math_500": null,
"aime": null,
"frontiermath": null,
"arc_agi_2": null,
"bfcl": null,
"tau_bench": null,
"osworld": null,
"simpleqa": null,
"mmmlu": null,
"mmlu_pro": null,
"live_code_bench": null,
"terminal_bench": null,
"webdev_arena_elo": null,
"mathvista": null,
"mmmu": null,
"mmmu_pro": null,
"lmarena_zh_elo": null,
"lmarena_vision_elo": null,
"livebench_reasoning": null,
"livebench_coding": null,
"livebench_agentic_coding": null,
"livebench_math": null,
"livebench_data_analysis": null,
"livebench_language": null,
"livebench_if": null
}
},
{
"id": "claude-opus-4-7-20260401",
"name": "Claude 4.7 Opus",
"aka": ["claude-opus-4-7", "claude-4.7-opus", "claude-4-7-opus"],
"provider": "Anthropic",
"type": "proprietary",
"release_date": "2026-04-01",
"pricing": {
"input_per_1m": 5.0,
"output_per_1m": 25.0,
"average_per_1m": 10.0
},
"performance": {
"output_speed_tps": 50,
"latency_ttft_ms": 0,
"source": "https://artificialanalysis.ai/models/claude-opus-4-7"
},
"editor_notes": "Anthropic's latest flagship model. Expensive and slower than average but boasts leading intelligence scores with a 1M token context window.",
"benchmark_scores": {
"lmarena_en_elo": 1498,
"lmarena_coding_elo": null,
"lmarena_hard_elo": null,
"lmarena_math_elo": null,
"lmarena_creative_elo": null,
"lmarena_if_elo": null,
"swe_bench": null,
"swe_bench_pro": null,
"gpqa_diamond": null,
"humanity_last_exam": null,
"livebench": null,
"math_500": null,
"aime": null,
"frontiermath": null,
"arc_agi_2": null,
"bfcl": null,
"tau_bench": null,
"osworld": null,
"simpleqa": null,
"mmmlu": null,
"mmlu_pro": null,
"live_code_bench": null,
"terminal_bench": null,
"webdev_arena_elo": null,
"mathvista": null,
"mmmu": null,
"mmmu_pro": null,
"lmarena_zh_elo": null,
"lmarena_vision_elo": null,
"livebench_reasoning": null,
"livebench_coding": null,
"livebench_agentic_coding": null,
"livebench_math": null,
"livebench_data_analysis": null,
"livebench_language": null,
"livebench_if": null
}
},
{
"id": "claude-opus-4-6-20260205",
"name": "Claude Opus 4.6",
Expand Down Expand Up @@ -149,7 +264,7 @@
"livebench": null,
"lmarena_coding_elo": 1547,
"lmarena_creative_elo": 1468,
"lmarena_en_elo": 1496,
"lmarena_en_elo": 1497,
"lmarena_hard_elo": 1529,
"lmarena_if_elo": 1500,
"lmarena_math_elo": 1501,
Expand Down Expand Up @@ -213,7 +328,7 @@
"livebench": 76.33,
"lmarena_coding_elo": 1556,
"lmarena_creative_elo": 1493,
"lmarena_en_elo": 1502,
"lmarena_en_elo": 1503,
"lmarena_hard_elo": 1536,
"lmarena_if_elo": 1512,
"lmarena_math_elo": 1512,
Expand Down Expand Up @@ -1053,7 +1168,7 @@
"livebench": 80.28,
"lmarena_coding_elo": 1532,
"lmarena_creative_elo": 1461,
"lmarena_en_elo": 1481,
"lmarena_en_elo": 1482,
"lmarena_hard_elo": 1507,
"lmarena_if_elo": 1488,
"lmarena_math_elo": 1522,
Expand Down
Loading