CoIR
Models retrieve relevant code or text across programming languages. The suite includes searches from code to code and from descriptions to code.
- Made by
- CoIR team
- Released
- July 2024
- Kind
- Function-level problems
- Level
- University
- Scored
- Checked automatically
- Answers
- Prediction
- Tasks
- All public
- Measures
- Capability
- Language
- English
- Interaction
- Single turn
- Refresh
- One fixed set
- Run by
- Anyone
Salesforce/SFR-Embedding-Code-2B_R tops the leaderboard with 67.4
Best score per entry from the benchmark's own leaderboard, read on November 20th, 2026. Where a model ran with several settings or harnesses, we keep its best. Names in gray aren't in our model list: fine-tunes, agent systems, products and older models. They don't count toward leaders.
- 1 Salesforce/SFR-Embedding-Code-2B_R 67.4
- 2 CodeSage-large-v2 64.2
- 3 Salesforce/SFR-Embedding-Code-400M_R 61.9
- 4 CodeSage-large 61.0
- 5 Voyage-Code-002 56.3
- 6 E5-Mistral 55.2
- 7 E5-Base-v2 50.9
- 8 OpenAI-Ada-002 45.6
- 9 BGE-Base-en-v1.5 42.8
- 10 BGE-M3 39.3
- 11 UniXcoder 37.3
- 12 GTE-Base-en-v1.5 36.8
- 13 Contriever 36.4
Source: Official CoIR leaderboard
| # | Entry | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Salesforce/SFR-Embedding-Code-2B_R 2B | 67.4 | Official leaderboard | ||
| 2 | CodeSage-large-v2 1.3B | 64.2 | Official leaderboard | ||
| 3 | Salesforce/SFR-Embedding-Code-400M_R 0.4B | 61.9 | Official leaderboard | ||
| 4 | CodeSage-large 1.3B | 61.0 | Official leaderboard | ||
| 5 | Voyage-Code-002 | 56.3 | Official leaderboard | ||
| 6 | E5-Mistral 7B | 55.2 | Official leaderboard | ||
| 7 | E5-Base-v2 0.1B | 50.9 | Official leaderboard | ||
| 8 | OpenAI-Ada-002 | 45.6 | Official leaderboard | ||
| 9 | BGE-Base-en-v1.5 0.1B | 42.8 | Official leaderboard | ||
| 10 | BGE-M3 0.6B | 39.3 | Official leaderboard | ||
| 11 | UniXcoder 0.1B | 37.3 | Official leaderboard | ||
| 12 | GTE-Base-en-v1.5 0.1B | 36.8 | Official leaderboard | ||
| 13 | Contriever 0.1B | 36.4 | Official leaderboard |
No lab model card reports it yet
We read the headline results of 540 launch posts from 57 labs, and none of them list this benchmark.
More in Coding
- SWE-bench Verified In use 500 human-validated GitHub issues from 12 Python repos. Agent writes a patch that must pass hidden tests. Claude Opus 4.7 83.5%
- LiveCodeBench v6 In use Competitive programming problems collected after model cutoffs from LeetCode, AtCoder, Codeforces. Scored pass@1 on hidden tests.
DeepSeek-V4-Pro 93.5%
- SWE-bench Multilingual In use 300 GitHub-issue tasks across nine programming languages in SWE-bench format. Patch graded by repository tests. Claude Fable 5.2 96.6%
- DeepSWE In use 113 original long-horizon engineering tasks across 91 repos and five languages, written from scratch. Hand-written verifiers accept alternative solutions. GPT-6 Astra 74.1%
- SciCode In use Scientist-curated research coding problems split into subproblems across natural sciences. Code checked against test cases.
Seed2.1 Pro 59.8%
- Codeforces rating In use Model solves recent Codeforces contest problems. An Elo-style rating is computed from simulated contest performance.
DeepSeek V4.1 Flash 3,471
Data audit
All 8 checks pass. Every benchmark
Catalog record 2 pass
- Pass Task access All tasks are public.
- Pass Confidence Checked against a primary source.
Scores 2 pass 3 notes
- Pass Independent runs Scores from the official leaderboard (13 entries).
- Pass Models scored 13 entries on its leaderboard, none a model we track.
- Note Newest score No scores yet.
- Note Frontier models No models scored yet.
- Note Headroom Scored as a plain number, with no fixed ceiling.
Leaderboard import 3 pass
- Pass Importer We read the board on archersama.github.io: 13 entries at the last read, none a model we track.
- Pass Last read November 20th, 2026.
- Pass Read worked The last read worked.
Consistency 1 pass 1 note
- Note Lab claims No model has both a lab number and an independent run.
- Pass Known issues No published audit found problems.