# OTelBench leaderboard

external benchmark

> Every figure below is reproduced as its upstream source published it: nothing is modelled, estimated, interpolated or converted. `Unavailable` means no source published the value — it is never a zero. Each value carries its evidence state and the date it was observed.

Page: https://modelscale.dev/leaderboards/benchmarks/external-otel-bench

OTelBench (OpenTelemetry instrumentation tasks). Every model the catalog carries a published OTelBench value for, ranked by that value.

## Benchmark record

| Field | Value |
| --- | --- |
| Category | external |
| Measure | Agent edits a service in a Linux terminal, Harbor framework |
| Tasks | 23 OpenTelemetry instrumentation tasks in 11 languages, three attempts each (69 runs) |
| Difficulty | Distributed tracing and context propagation across services |
| Published by | [Benchmarking OpenTelemetry: can AI trace your failed login? (Quesma)](https://quesma.com/blog/introducing-otel-bench/) |

Quesma's OTelBench asks coding agents to add OpenTelemetry tracing, metrics and logging to small existing services in 11 programming languages. The score is the share of runs where the service then emits correct telemetry.

## OTelBench ranking

13 models with a published OTelBench value, ordered by that value, highest first. Models the source has not scored on this benchmark are not listed — they are unmeasured, not last.

| Rank | Model | Provider | Agent edits a service in a Linux terminal, Harbor framework | Evidence |
| --- | --- | --- | --- | --- |
| 1 | [Claude Opus 4.5](https://modelscale.dev/models/claude-opus-4-5) | Anthropic | 29.0 | Observed 2026-11-21 · source benchlm:models |
| 2 | [GPT-5.2](https://modelscale.dev/models/gpt-5-2) | OpenAI | 26.1 | Observed 2026-11-21 · source benchlm:models |
| 3 | [Claude Sonnet 4.5](https://modelscale.dev/models/claude-sonnet-4-5) | Anthropic | 21.7 | Observed 2026-11-21 · source benchlm:models |
| 4 | [Gemini 3 Flash](https://modelscale.dev/models/gemini-3-flash) | Google | 18.8 | Observed 2026-11-21 · source benchlm:models |
| 5 | [Gemini 3 Pro](https://modelscale.dev/models/gemini-3-pro) | Google | 15.9 | Observed 2026-11-21 · source benchlm:models |
| 5 | [GPT-5.2-Codex](https://modelscale.dev/models/gpt-5-2-codex) | OpenAI | 15.9 | Observed 2026-11-21 · source benchlm:models |
| 7 | [GPT-5.1](https://modelscale.dev/models/gpt-5-1) | OpenAI | 14.5 | Observed 2026-11-21 · source benchlm:models |
| 8 | [GLM-4.7](https://modelscale.dev/models/glm-4-7) | Z.AI | 13.0 | Observed 2026-11-21 · source benchlm:models |
| 9 | [DeepSeek V3.2](https://modelscale.dev/models/deepseek-v3-2) | DeepSeek | 11.6 | Observed 2026-11-21 · source benchlm:models |
| 9 | [GPT-5.1-Codex-Max](https://modelscale.dev/models/gpt-5-1-codex-max) | OpenAI | 11.6 | Observed 2026-11-21 · source benchlm:models |
| 11 | [Claude Haiku 4.5](https://modelscale.dev/models/claude-haiku-4-5) | Anthropic | 5.8 | Observed 2026-11-21 · source benchlm:models |
| 12 | [Grok 4](https://modelscale.dev/models/grok-4) | xAI | 4.3 | Observed 2026-11-21 · source benchlm:models |
| 13 | [Grok 4.1 Fast](https://modelscale.dev/models/grok-4-1-fast) | xAI | 2.9 | Observed 2026-11-21 · source benchlm:models |

Rows are ordered by the value the source published, highest first. The source does not state whether a higher value is the better result, so this document does not either: for a benchmark that measures a rate of failure, read the table from the bottom.
