Claude Haiku 4.5 vs GPT-OSS 120B
Change modelsClaude Haiku 4.5Anthropic
GPT-OSS 120BOpenAI
IndexAll categories, out of 100.
43.2 ±4.2
43.4 ±4.2 best
GapIndex points below the top.
−0.2 · no clear gap
Top
CoverageIndex weight that has results.
95% best
90%
SpeedOutput tokens per second.
88/s best
34/s
EloLMArena rating and rank.
1397 best
1365
ReleasedMonth of release.
2025-10
2025-08
Input / 1MUS dollars per 1M input tokens.
$1.00
$0.15 best
Output / 1MUS dollars per 1M output tokens.
$5.00
$0.60 best
Batch output / 1MBatch price per 1M output tokens.
$2.50
—
1K chats2K tokens in, 500 out, each.
$4.50
$0.60 best
1K documents20K tokens in, 1K out, each.
$25.00
$3.60 best
1K agent tasks200K tokens in, 20K out, each.
$300.00
$42.00 best
ContextMaximum tokens in one request.
200K best
131K
AgenticMulti-step tasks with tools.
48.9 best
40.1
CodingCode writing and repair.
49.9 best
42.8
ReasoningLogic problems and puzzles.
38.1
40.2 best
MultimodalTasks with images and text.
42.6
—
KnowledgeFacts and expert knowledge.
36.1
42.4 best
MultilingualTasks in many languages.
44.5
51.1 best
InstructionTasks with strict prompt rules.
—
53.5
MathMath problems.
40.5
51.5 best
Benchmarks
13 sharedOnly Claude Haiku 4.5: 25Only GPT-OSS 120B: 35
Claude Haiku 4.5
GPT-OSS 120B